{ "values": { "messages": [ { "content": [ { "type": "text", "text": "Conduct a research on https://github.com/bytedance/deer-flow" } ], "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": "7da141e4-3ab2-43d0-8485-5128f623c0c4" }, { "content": "", "additional_kwargs": { "reasoning_content": "The user wants me to conduct research on the GitHub repository https://github.com/bytedance/deer-flow. This is a GitHub repository URL, which matches the github-deep-research skill. The skill is designed for comprehensive analysis of GitHub repos. I should first load the skill file to understand the workflow, then follow it.\n\nFirst, I need to check if there are any uploaded files. The system prompt mentions uploaded files are listed before each request, but I don't see an section. So I'll proceed.\n\nI should load the github-deep-research skill first. The path is /mnt/skills/public/github-deep-research/SKILL.md. Let me read it." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1712-c6d9-7ff3-b2b2-f1d9e0bffc57", "tool_calls": [ { "name": "read_file", "args": { "description": "Load github-deep-research skill to understand workflow for analyzing GitHub repositories", "path": "/mnt/skills/public/github-deep-research/SKILL.md" }, "id": "call_51eahgxphy8jjw9zqgvvihlz", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "---\nname: github-deep-research\ndescription: Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.\n---\n\n# GitHub Deep Research Skill\n\nMulti-round research combining GitHub API, web_search, web_fetch to produce comprehensive markdown reports.\n\n## Research Workflow\n\n- Round 1: GitHub API\n- Round 2: Discovery\n- Round 3: Deep Investigation\n- Round 4: Deep Dive\n\n## Core Methodology\n\n### Query Strategy\n\n**Broad to Narrow**: Start with GitHub API, then general queries, refine based on findings.\n\n```\nRound 1: GitHub API\nRound 2: \"{topic} overview\"\nRound 3: \"{topic} architecture\", \"{topic} vs alternatives\"\nRound 4: \"{topic} issues\", \"{topic} roadmap\", \"site:github.com {topic}\"\n```\n\n**Source Prioritization**:\n1. Official docs/repos (highest weight)\n2. Technical blogs (Medium, Dev.to)\n3. News articles (verified outlets)\n4. Community discussions (Reddit, HN)\n5. Social media (lowest weight, for sentiment)\n\n### Research Rounds\n\n**Round 1 - GitHub API**\nDirectly execute `scripts/github_api.py` without `read_file()`:\n```bash\npython /path/to/skill/scripts/github_api.py summary\npython /path/to/skill/scripts/github_api.py readme\npython /path/to/skill/scripts/github_api.py tree\n```\n\n**Available commands (the last argument of `github_api.py`):**\n- summary\n- info\n- readme\n- tree\n- languages\n- contributors\n- commits\n- issues\n- prs\n- releases\n\n**Round 2 - Discovery (3-5 web_search)**\n- Get overview and identify key terms\n- Find official website/repo\n- Identify main players/competitors\n\n**Round 3 - Deep Investigation (5-10 web_search + web_fetch)**\n- Technical architecture details\n- Timeline of key events\n- Community sentiment\n- Use web_fetch on valuable URLs for full content\n\n**Round 4 - Deep Dive**\n- Analyze commit history for timeline\n- Review issues/PRs for feature evolution\n- Check contributor activity\n\n## Report Structure\n\nFollow template in `assets/report_template.md`:\n\n1. **Metadata Block** - Date, confidence level, subject\n2. **Executive Summary** - 2-3 sentence overview with key metrics\n3. **Chronological Timeline** - Phased breakdown with dates\n4. **Key Analysis Sections** - Topic-specific deep dives\n5. **Metrics & Comparisons** - Tables, growth charts\n6. **Strengths & Weaknesses** - Balanced assessment\n7. **Sources** - Categorized references\n8. **Confidence Assessment** - Claims by confidence level\n9. **Methodology** - Research approach used\n\n### Mermaid Diagrams\n\nInclude diagrams where helpful:\n\n**Timeline (Gantt)**:\n```mermaid\ngantt\n title Project Timeline\n dateFormat YYYY-MM-DD\n section Phase 1\n Development :2025-01-01, 2025-03-01\n section Phase 2\n Launch :2025-03-01, 2025-04-01\n```\n\n**Architecture (Flowchart)**:\n```mermaid\nflowchart TD\n A[User] --> B[Coordinator]\n B --> C[Planner]\n C --> D[Research Team]\n D --> E[Reporter]\n```\n\n**Comparison (Pie/Bar)**:\n```mermaid\npie title Market Share\n \"Project A\" : 45\n \"Project B\" : 30\n \"Others\" : 25\n```\n\n## Confidence Scoring\n\nAssign confidence based on source quality:\n\n| Confidence | Criteria |\n|------------|----------|\n| High (90%+) | Official docs, GitHub data, multiple corroborating sources |\n| Medium (70-89%) | Single reliable source, recent articles |\n| Low (50-69%) | Social media, unverified claims, outdated info |\n\n## Output\n\nSave report as: `research_{topic}_{YYYYMMDD}.md`\n\n### Formatting Rules\n\n- Chinese content: Use full-width punctuation（，。：；！？）\n- Technical terms: Provide Wiki/doc URL on first mention\n- Tables: Use for metrics, comparisons\n- Code blocks: For technical examples\n- Mermaid: For architecture, timelines, flows\n\n## Best Practices\n\n1. **Start with official sources** - Repo, docs, company blog\n2. **Verify dates from commits/PRs** - More reliable than articles\n3. **Triangulate claims** - 2+ independent sources\n4. **Note conflicting info** - Don't hide contradictions\n5. **Distinguish fact vs opinion** - Label speculation clearly\n6. **Cite inline** - Reference sources near claims\n7. **Update as you go** - Don't wait until end to synthesize\n", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "read_file", "id": "4bf0cb1a-a66c-4eb9-81f9-5106f0e331a8", "tool_call_id": "call_51eahgxphy8jjw9zqgvvihlz", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to start the research on the DeerFlow repository. First, I should parse the GitHub URL to get owner and repo. The URL is https://github.com/bytedance/deer-flow, so owner is \"bytedance\" and repo is \"deer-flow\". I'll start with Round 1: GitHub API.\n\nLet me first check what scripts are available in the skill directory. I should list the directory to see the structure." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1712-f6e3-7c33-a3e6-aa12a34fa1a0", "tool_calls": [ { "name": "ls", "args": { "description": "Check github-deep-research skill directory structure", "path": "/mnt/skills/public/github-deep-research" }, "id": "call_yfdgoa2kxdfeiar8340cf035", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "/mnt/skills/public/github-deep-research\n/mnt/skills/public/github-deep-research/scripts\n/mnt/skills/public/github-deep-research/scripts/github_api.py\n/mnt/skills/public/github-deep-research/SKILL.md\n/mnt/skills/public/github-deep-research/assets\n/mnt/skills/public/github-deep-research/assets/report_template.md", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "ls", "id": "a8f483fd-1b99-44bc-adf5-285036d897eb", "tool_call_id": "call_yfdgoa2kxdfeiar8340cf035", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to parse the GitHub URL to get owner and repo. The URL is https://github.com/bytedance/deer-flow. So owner is \"bytedance\", repo is \"deer-flow\". Let me start by creating a todo list for this multi-step research task." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1713-1a05-7790-9654-8f80bb14d82f", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "in_progress" }, { "content": "Fetch README and repository information", "status": "pending" }, { "content": "Analyze repository structure and languages", "status": "pending" }, { "content": "Research DeerFlow project overview and purpose", "status": "pending" }, { "content": "Investigate technical architecture and features", "status": "pending" }, { "content": "Analyze community activity and contributors", "status": "pending" }, { "content": "Research timeline and development history", "status": "pending" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_b0zngt5ncnuy0bzs245pk4zl", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'in_progress'}, {'content': 'Fetch README and repository information', 'status': 'pending'}, {'content': 'Analyze repository structure and languages', 'status': 'pending'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'pending'}, {'content': 'Investigate technical architecture and features', 'status': 'pending'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "dde76919-20df-4225-bfcf-a8ec19d2a1d9", "tool_call_id": "call_b0zngt5ncnuy0bzs245pk4zl", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to start with Round 1: GitHub API. First extract the owner and repo from the URL: https://github.com/bytedance/deer-flow. Owner: bytedance, repo: deer-flow. Let's run the GitHub API commands." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1713-44eb-73f1-9ab0-c18c0635e3c8", "tool_calls": [ { "name": "bash", "args": { "description": "Run GitHub API to get repository summary", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow summary" }, "id": "call_14ov252og9xq2jbzk6jw8ws6", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "{\n \"name\": \"bytedance/deer-flow\",\n \"description\": \"DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.\",\n \"url\": \"https://github.com/bytedance/deer-flow\",\n \"stars\": 19531,\n \"forks\": 2452,\n \"open_issues\": 196,\n \"language\": \"Python\",\n \"license\": \"MIT\",\n \"created_at\": \"2025-05-07T02:50:19Z\",\n \"updated_at\": \"2026-02-01T01:07:38Z\",\n \"pushed_at\": \"2026-01-30T00:47:23Z\",\n \"default_branch\": \"main\",\n \"topics\": [\n \"agent\",\n \"agentic\",\n \"agentic-framework\",\n \"agentic-workflow\",\n \"ai\",\n \"ai-agents\",\n \"bytedance\",\n \"deep-research\",\n \"langchain\",\n \"langgraph\",\n \"langmanus\",\n \"llm\",\n \"multi-agent\",\n \"nodejs\",\n \"podcast\",\n \"python\",\n \"typescript\"\n ],\n \"languages\": {\n \"Python\": 1292574,\n \"TypeScript\": 503143,\n \"CSS\": 15128,\n \"JavaScript\": 7906,\n \"Dockerfile\": 2197,\n \"Makefile\": 1352,\n \"Shell\": 1152,\n \"Batchfile\": 497\n },\n \"contributor_count\": 88\n}", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "7ecf6cb9-abb9-44b9-bbef-743fd874c718", "tool_call_id": "call_14ov252og9xq2jbzk6jw8ws6", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to update the todo list and continue with the next steps. Let me mark the first task as completed and start the second one." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1713-758e-7100-bb7e-a4def93ad9c0", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "in_progress" }, { "content": "Analyze repository structure and languages", "status": "pending" }, { "content": "Research DeerFlow project overview and purpose", "status": "pending" }, { "content": "Investigate technical architecture and features", "status": "pending" }, { "content": "Analyze community activity and contributors", "status": "pending" }, { "content": "Research timeline and development history", "status": "pending" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_eqiy7phiv0pmuujmt0y6pulb", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'in_progress'}, {'content': 'Analyze repository structure and languages', 'status': 'pending'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'pending'}, {'content': 'Investigate technical architecture and features', 'status': 'pending'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "023fc38d-c64b-446d-8a2a-dda90369b1f9", "tool_call_id": "call_eqiy7phiv0pmuujmt0y6pulb", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to fetch the README and more repository information. Let me run the GitHub API for README and other details." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1713-998a-7553-b4eb-9c6a53ac00b1", "tool_calls": [ { "name": "bash", "args": { "description": "Get README content from repository", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow readme" }, "id": "call_semgkgyfsd7f76uzwzgk3ja9", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![DeepWiki](https://img.shields.io/badge/DeepWiki-bytedance%2Fdeer--flow-blue.svg?logo=data:image/png;base64,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)](https://deepwiki.com/bytedance/deer-flow)\n\n\n\n[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)\n\n> Originated from Open Source, give back to Open Source.\n\n> [!NOTE]\n> As we're [moving to DeerFlow 2.0](https://github.com/bytedance/deer-flow/issues/824) in February, it's time to wrap up DeerFlow 1.0 on the main branch.\n\n**DeerFlow** (**D**eep **E**xploration and **E**fficient **R**esearch **Flow**) is a community-driven Deep Research framework that builds upon the incredible work of the open source community. Our goal is to combine language models with specialized tools for tasks like web search, crawling, and Python code execution, while giving back to the community that made this possible.\n\nCurrently, DeerFlow has officially entered the [FaaS Application Center of Volcengine](https://console.volcengine.com/vefaas/region:vefaas+cn-beijing/market). Users can experience it online through the [experience link](https://console.volcengine.com/vefaas/region:vefaas+cn-beijing/market/deerflow/?channel=github&source=deerflow) to intuitively feel its powerful functions and convenient operations. At the same time, to meet the deployment needs of different users, DeerFlow supports one-click deployment based on Volcengine. Click the [deployment link](https://console.volcengine.com/vefaas/region:vefaas+cn-beijing/application/create?templateId=683adf9e372daa0008aaed5c&channel=github&source=deerflow) to quickly complete the deployment process and start an efficient research journey.\n\nDeerFlow has newly integrated the intelligent search and crawling toolset independently developed by BytePlus--[InfoQuest (supports free online experience)](https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest)\n\n\n \n\n\nPlease visit [our official website](https://deerflow.tech/) for more details.\n\n## Demo\n\n### Video\n\n\n\nIn this demo, we showcase how to use DeerFlow to:\n\n- Seamlessly integrate with MCP services\n- Conduct the Deep Research process and produce a comprehensive report with images\n- Create podcast audio based on the generated report\n\n### Replays\n\n- [How tall is Eiffel Tower compared to tallest building?](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)\n- [What are the top trending repositories on GitHub?](https://deerflow.tech/chat?replay=github-top-trending-repo)\n- [Write an article about Nanjing's traditional dishes](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)\n- [How to decorate a rental apartment?](https://deerflow.tech/chat?replay=rental-apartment-decoration)\n- [Visit our official website to explore more replays.](https://deerflow.tech/#case-studies)\n\n---\n\n## 📑 Table of Contents\n\n- [🚀 Quick Start](#quick-start)\n- [🌟 Features](#features)\n- [🏗️ Architecture](#architecture)\n- [🛠️ Development](#development)\n- [🐳 Docker](#docker)\n- [🗣️ Text-to-Speech Integration](#text-to-speech-integration)\n- [📚 Examples](#examples)\n- [❓ FAQ](#faq)\n- [📜 License](#license)\n- [💖 Acknowledgments](#acknowledgments)\n- [⭐ Star History](#star-history)\n\n## Quick Start\n\nDeerFlow is developed in Python, and comes with a web UI written in Node.js. To ensure a smooth setup process, we recommend using the following tools:\n\n### Recommended Tools\n\n- **[`uv`](https://docs.astral.sh/uv/getting-started/installation/):**\n Simplify Python environment and dependency management. `uv` automatically creates a virtual environment in the root directory and installs all required packages for you—no need to manually install Python environments.\n\n- **[`nvm`](https://github.com/nvm-sh/nvm):**\n Manage multiple versions of the Node.js runtime effortlessly.\n\n- **[`pnpm`](https://pnpm.io/installation):**\n Install and manage dependencies of Node.js project.\n\n### Environment Requirements\n\nMake sure your system meets the following minimum requirements:\n\n- **[Python](https://www.python.org/downloads/):** Version `3.12+`\n- **[Node.js](https://nodejs.org/en/download/):** Version `22+`\n\n### Installation\n\n```bash\n# Clone the repository\ngit clone https://github.com/bytedance/deer-flow.git\ncd deer-flow\n\n# Install dependencies, uv will take care of the python interpreter and venv creation, and install the required packages\nuv sync\n\n# Configure .env with your API keys\n# Tavily: https://app.tavily.com/home\n# Brave_SEARCH: https://brave.com/search/api/\n# volcengine TTS: Add your TTS credentials if you have them\ncp .env.example .env\n\n# See the 'Supported Search Engines' and 'Text-to-Speech Integration' sections below for all available options\n\n# Configure conf.yaml for your LLM model and API keys\n# Please refer to 'docs/configuration_guide.md' for more details\n# For local development, you can use Ollama or other local models\ncp conf.yaml.example conf.yaml\n\n# Install marp for ppt generation\n# https://github.com/marp-team/marp-cli?tab=readme-ov-file#use-package-manager\nbrew install marp-cli\n```\n\nOptionally, install web UI dependencies via [pnpm](https://pnpm.io/installation):\n\n```bash\ncd deer-flow/web\npnpm install\n```\n\n### Configurations\n\nPlease refer to the [Configuration Guide](docs/configuration_guide.md) for more details.\n\n> [!NOTE]\n> Before you start the project, read the guide carefully, and update the configurations to match your specific settings and requirements.\n\n### Console UI\n\nThe quickest way to run the project is to use the console UI.\n\n```bash\n# Run the project in a bash-like shell\nuv run main.py\n```\n\n### Web UI\n\nThis project also includes a Web UI, offering a more dynamic and engaging interactive experience.\n\n> [!NOTE]\n> You need to install the dependencies of web UI first.\n\n```bash\n# Run both the backend and frontend servers in development mode\n# On macOS/Linux\n./bootstrap.sh -d\n\n# On Windows\nbootstrap.bat -d\n```\n> [!Note]\n> By default, the backend server binds to 127.0.0.1 (localhost) for security reasons. If you need to allow external connections (e.g., when deploying on Linux server), you can modify the server host to 0.0.0.0 in the bootstrap script(uv run server.py --host 0.0.0.0).\n> Please ensure your environment is properly secured before exposing the service to external networks.\n\nOpen your browser and visit [`http://localhost:3000`](http://localhost:3000) to explore the web UI.\n\nExplore more details in the [`web`](./web/) directory.\n\n## Supported Search Engines\n\n### Web Search\n\nDeerFlow supports multiple search engines that can be configured in your `.env` file using the `SEARCH_API` variable:\n\n- **Tavily** (default): A specialized search API for AI applications\n - Requires `TAVILY_API_KEY` in your `.env` file\n - Sign up at: https://app.tavily.com/home\n\n- **InfoQuest** (recommended): AI-optimized intelligent search and crawling toolset independently developed by BytePlus\n - Requires `INFOQUEST_API_KEY` in your `.env` file\n - Support for time range filtering and site filtering\n - Provides high-quality search results and content extraction\n - Sign up at: https://console.byteplus.com/infoquest/infoquests\n - Visit https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest to learn more\n\n- **DuckDuckGo**: Privacy-focused search engine\n - No API key required\n\n- **Brave Search**: Privacy-focused search engine with advanced features\n - Requires `BRAVE_SEARCH_API_KEY` in your `.env` file\n - Sign up at: https://brave.com/search/api/\n\n- **Arxiv**: Scientific paper search for academic research\n - No API key required\n - Specialized for scientific and academic papers\n\n- **Searx/SearxNG**: Self-hosted metasearch engine\n - Requires `SEARX_HOST` to be set in the `.env` file\n - Supports connecting to either Searx or SearxNG\n\nTo configure your preferred search engine, set the `SEARCH_API` variable in your `.env` file:\n\n```bash\n# Choose one: tavily, infoquest, duckduckgo, brave_search, arxiv\nSEARCH_API=tavily\n```\n\n### Crawling Tools\n\nDeerFlow supports multiple crawling tools that can be configured in your `conf.yaml` file:\n\n- **Jina** (default): Freely accessible web content crawling tool\n\n- **InfoQuest** (recommended): AI-optimized intelligent search and crawling toolset developed by BytePlus\n - Requires `INFOQUEST_API_KEY` in your `.env` file\n - Provides configurable crawling parameters\n - Supports custom timeout settings\n - Offers more powerful content extraction capabilities\n - Visit https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest to learn more\n\nTo configure your preferred crawling tool, set the following in your `conf.yaml` file:\n\n```yaml\nCRAWLER_ENGINE:\n # Engine type: \"jina\" (default) or \"infoquest\"\n engine: infoquest\n```\n\n### Private Knowledgebase\n\nDeerFlow supports private knowledgebase such as RAGFlow, Qdrant, Milvus, and VikingDB, so that you can use your private documents to answer questions.\n\n- **[RAGFlow](https://ragflow.io/docs/dev/)**: open source RAG engine\n ```bash\n # examples in .env.example\n RAG_PROVIDER=ragflow\n RAGFLOW_API_URL=\"http://localhost:9388\"\n RAGFLOW_API_KEY=\"ragflow-xxx\"\n RAGFLOW_RETRIEVAL_SIZE=10\n RAGFLOW_CROSS_LANGUAGES=English,Chinese,Spanish,French,German,Japanese,Korean\n ```\n\n- **[Qdrant](https://qdrant.tech/)**: open source vector database\n ```bash\n # Using Qdrant Cloud or self-hosted\n RAG_PROVIDER=qdrant\n QDRANT_LOCATION=https://xyz-example.eu-central.aws.cloud.qdrant.io:6333\n QDRANT_API_KEY=your_qdrant_api_key\n QDRANT_COLLECTION=documents\n QDRANT_EMBEDDING_PROVIDER=openai\n QDRANT_EMBEDDING_MODEL=text-embedding-ada-002\n QDRANT_EMBEDDING_API_KEY=your_openai_api_key\n QDRANT_AUTO_LOAD_EXAMPLES=true\n ```\n\n## Features\n\n### Core Capabilities\n\n- 🤖 **LLM Integration**\n - It supports the integration of most models through [litellm](https://docs.litellm.ai/docs/providers).\n - Support for open source models like Qwen, you need to read the [configuration](docs/configuration_guide.md) for more details.\n - OpenAI-compatible API interface\n - Multi-tier LLM system for different task complexities\n\n### Tools and MCP Integrations\n\n- 🔍 **Search and Retrieval**\n - Web search via Tavily, InfoQuest, Brave Search and more\n - Crawling with Jina and InfoQuest\n - Advanced content extraction\n - Support for private knowledgebase\n\n- 📃 **RAG Integration**\n\n - Supports multiple vector databases: [Qdrant](https://qdrant.tech/), [Milvus](https://milvus.io/), [RAGFlow](https://github.com/infiniflow/ragflow), VikingDB, MOI, and Dify\n - Supports mentioning files from RAG providers within the input box\n - Easy switching between different vector databases through configuration\n\n- 🔗 **MCP Seamless Integration**\n - Expand capabilities for private domain access, knowledge graph, web browsing and more\n - Facilitates integration of diverse research tools and methodologies\n\n### Human Collaboration\n\n- 💬 **Intelligent Clarification Feature**\n - Multi-turn dialogue to clarify vague research topics\n - Improve research precision and report quality\n - Reduce ineffective searches and token usage\n - Configurable switch for flexible enable/disable control\n - See [Configuration Guide - Clarification](./docs/configuration_guide.md#multi-turn-clarification-feature) for details\n\n- 🧠 **Human-in-the-loop**\n - Supports interactive modification of research plans using natural language\n - Supports auto-acceptance of research plans\n\n- 📝 **Report Post-Editing**\n - Supports Notion-like block editing\n - Allows AI refinements, including AI-assisted polishing, sentence shortening, and expansion\n - Powered by [tiptap](https://tiptap.dev/)\n\n### Content Creation\n\n- 🎙️ **Podcast and Presentation Generation**\n - AI-powered podcast script generation and audio synthesis\n - Automated creation of simple PowerPoint presentations\n - Customizable templates for tailored content\n\n## Architecture\n\nDeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis. The system is built on LangGraph, enabling a flexible state-based workflow where components communicate through a well-defined message passing system.\n\n![Architecture Diagram](./assets/architecture.png)\n\n> See it live at [deerflow.tech](https://deerflow.tech/#multi-agent-architecture)\n\nThe system employs a streamlined workflow with the following components:\n\n1. **Coordinator**: The entry point that manages the workflow lifecycle\n\n - Initiates the research process based on user input\n - Delegates tasks to the planner when appropriate\n - Acts as the primary interface between the user and the system\n\n2. **Planner**: Strategic component for task decomposition and planning\n\n - Analyzes research objectives and creates structured execution plans\n - Determines if enough context is available or if more research is needed\n - Manages the research flow and decides when to generate the final report\n\n3. **Research Team**: A collection of specialized agents that execute the plan:\n - **Researcher**: Conducts web searches and information gathering using tools like web search engines, crawling and even MCP services.\n - **Coder**: Handles code analysis, execution, and technical tasks using Python REPL tool.\n Each agent has access to specific tools optimized for their role and operates within the LangGraph framework\n\n4. **Reporter**: Final stage processor for research outputs\n - Aggregates findings from the research team\n - Processes and structures the collected information\n - Generates comprehensive research reports\n\n## Text-to-Speech Integration\n\nDeerFlow now includes a Text-to-Speech (TTS) feature that allows you to convert research reports to speech. This feature uses the volcengine TTS API to generate high-quality audio from text. Features like speed, volume, and pitch are also customizable.\n\n### Using the TTS API\n\nYou can access the TTS functionality through the `/api/tts` endpoint:\n\n```bash\n# Example API call using curl\ncurl --location 'http://localhost:8000/api/tts' \\\n--header 'Content-Type: application/json' \\\n--data '{\n \"text\": \"This is a test of the text-to-speech functionality.\",\n \"speed_ratio\": 1.0,\n \"volume_ratio\": 1.0,\n \"pitch_ratio\": 1.0\n}' \\\n--output speech.mp3\n```\n\n## Development\n\n### Testing\nInstall development dependencies:\n\n```bash\nuv pip install -e \".[test]\"\n```\n\n\nRun the test suite:\n\n```bash\n# Run all tests\nmake test\n\n# Run specific test file\npytest tests/integration/test_workflow.py\n\n# Run with coverage\nmake coverage\n```\n\n### Code Quality\n\n```bash\n# Run linting\nmake lint\n\n# Format code\nmake format\n```\n\n### Debugging with LangGraph Studio\n\nDeerFlow uses LangGraph for its workflow architecture. You can use LangGraph Studio to debug and visualize the workflow in real-time.\n\n#### Running LangGraph Studio Locally\n\nDeerFlow includes a `langgraph.json` configuration file that defines the graph structure and dependencies for the LangGraph Studio. This file points to the workflow graphs defined in the project and automatically loads environment variables from the `.env` file.\n\n##### Mac\n\n```bash\n# Install uv package manager if you don't have it\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n# Install dependencies and start the LangGraph server\nuvx --refresh --from \"langgraph-cli[inmem]\" --with-editable . --python 3.12 langgraph dev --allow-blocking\n```\n\n##### Windows / Linux\n\n```bash\n# Install dependencies\npip install -e .\npip install -U \"langgraph-cli[inmem]\"\n\n# Start the LangGraph server\nlanggraph dev\n```\n\nAfter starting the LangGraph server, you'll see several URLs in the terminal:\n\n- API: http://127.0.0.1:2024\n- Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024\n- API Docs: http://127.0.0.1:2024/docs\n\nOpen the Studio UI link in your browser to access the debugging interface.\n\n#### Using LangGraph Studio\n\nIn the Studio UI, you can:\n\n1. Visualize the workflow graph and see how components connect\n2. Trace execution in real-time to see how data flows through the system\n3. Inspect the state at each step of the workflow\n4. Debug issues by examining inputs and outputs of each component\n5. Provide feedback during the planning phase to refine research plans\n\nWhen you submit a research topic in the Studio UI, you'll be able to see the entire workflow execution, including:\n\n- The planning phase where the research plan is created\n- The feedback loop where you can modify the plan\n- The research and writing phases for each section\n- The final report generation\n\n### Enabling LangSmith Tracing\n\nDeerFlow supports LangSmith tracing to help you debug and monitor your workflows. To enable LangSmith tracing:\n\n1. Make sure your `.env` file has the following configurations (see `.env.example`):\n\n ```bash\n LANGSMITH_TRACING=true\n LANGSMITH_ENDPOINT=\"https://api.smith.langchain.com\"\n LANGSMITH_API_KEY=\"xxx\"\n LANGSMITH_PROJECT=\"xxx\"\n ```\n\n2. Start tracing and visualize the graph locally with LangSmith by running:\n ```bash\n langgraph dev\n ```\n\nThis will enable trace visualization in LangGraph Studio and send your traces to LangSmith for monitoring and analysis.\n\n### Checkpointing\n1. Postgres and MonogDB implementation of LangGraph checkpoint saver.\n2. In-memory store is used to caching the streaming messages before persisting to database, If finish_reason is \"stop\" or \"interrupt\", it triggers persistence.\n3. Supports saving and loading checkpoints for workflow execution.\n4. Supports saving chat stream events for replaying conversations.\n\n*Note: About langgraph issue #5557*\nThe latest langgraph-checkpoint-postgres-2.0.23 have checkpointing issue, you can check the open issue:\"TypeError: Object of type HumanMessage is not JSON serializable\" [https://github.com/langchain-ai/langgraph/issues/5557].\n\nTo use postgres checkpoint you should install langgraph-checkpoint-postgres-2.0.21\n\n*Note: About psycopg dependencies*\nPlease read the following document before using postgres: https://www.psycopg.org/psycopg3/docs/basic/install.html\n\nBY default, psycopg needs libpq to be installed on your system. If you don't have libpq installed, you can install psycopg with the `binary` extra to include a statically linked version of libpq mannually:\n\n```bash\npip install psycopg[binary]\n```\nThis will install a self-contained package with all the libraries needed, but binary not supported for all platform, you check the supported platform : https://pypi.org/project/psycopg-binary/#files\n\nif not supported, you can select local-installation: https://www.psycopg.org/psycopg3/docs/basic/install.html#local-installation\n\n\nThe default database and collection will be automatically created if not exists.\nDefault database: checkpoing_db\nDefault collection: checkpoint_writes_aio (langgraph checkpoint writes)\nDefault collection: checkpoints_aio (langgraph checkpoints)\nDefault collection: chat_streams (chat stream events for replaying conversations)\n\nYou need to set the following environment variables in your `.env` file:\n\n```bash\n# Enable LangGraph checkpoint saver, supports MongoDB, Postgres\nLANGGRAPH_CHECKPOINT_SAVER=true\n# Set the database URL for saving checkpoints\nLANGGRAPH_CHECKPOINT_DB_URL=\"mongodb://localhost:27017/\"\n#LANGGRAPH_CHECKPOINT_DB_URL=postgresql://localhost:5432/postgres\n```\n\n## Docker\n\nYou can also run this project with Docker.\n\nFirst, you need read the [configuration](docs/configuration_guide.md) below. Make sure `.env`, `.conf.yaml` files are ready.\n\nSecond, to build a Docker image of your own web server:\n\n```bash\ndocker build -t deer-flow-api .\n```\n\nFinal, start up a docker container running the web server:\n```bash\n# Replace deer-flow-api-app with your preferred container name\n# Start the server then bind to localhost:8000\ndocker run -d -t -p 127.0.0.1:8000:8000 --env-file .env --name deer-flow-api-app deer-flow-api\n\n# stop the server\ndocker stop deer-flow-api-app\n```\n\n### Docker Compose (include both backend and frontend)\n\nDeerFlow provides a docker-compose setup to easily run both the backend and frontend together:\n\n```bash\n# building docker image\ndocker compose build\n\n# start the server\ndocker compose up\n```\n\n> [!WARNING]\n> If you want to deploy the deer flow into production environments, please add authentication to the website and evaluate your security check of the MCPServer and Python Repl.\n\n## Examples\n\nThe following examples demonstrate the capabilities of DeerFlow:\n\n### Research Reports\n\n1. **OpenAI Sora Report** - Analysis of OpenAI's Sora AI tool\n\n - Discusses features, access, prompt engineering, limitations, and ethical considerations\n - [View full report](examples/openai_sora_report.md)\n\n2. **Google's Agent to Agent Protocol Report** - Overview of Google's Agent to Agent (A2A) protocol\n\n - Discusses its role in AI agent communication and its relationship with Anthropic's Model Context Protocol (MCP)\n - [View full report](examples/what_is_agent_to_agent_protocol.md)\n\n3. **What is MCP?** - A comprehensive analysis of the term \"MCP\" across multiple contexts\n\n - Explores Model Context Protocol in AI, Monocalcium Phosphate in chemistry, and Micro-channel Plate in electronics\n - [View full report](examples/what_is_mcp.md)\n\n4. **Bitcoin Price Fluctuations** - Analysis of recent Bitcoin price movements\n\n - Examines market trends, regulatory influences, and technical indicators\n - Provides recommendations based on historical data\n - [View full report](examples/bitcoin_price_fluctuation.md)\n\n5. **What is LLM?** - An in-depth exploration of Large Language Models\n\n - Discusses architecture, training, applications, and ethical considerations\n - [View full report](examples/what_is_llm.md)\n\n6. **How to Use Claude for Deep Research?** - Best practices and workflows for using Claude in deep research\n\n - Covers prompt engineering, data analysis, and integration with other tools\n - [View full report](examples/how_to_use_claude_deep_research.md)\n\n7. **AI Adoption in Healthcare: Influencing Factors** - Analysis of factors driving AI adoption in healthcare\n\n - Discusses AI technologies, data quality, ethical considerations, economic evaluations, organizational readiness, and digital infrastructure\n - [View full report](examples/AI_adoption_in_healthcare.md)\n\n8. **Quantum Computing Impact on Cryptography** - Analysis of quantum computing's impact on cryptography\n\n - Discusses vulnerabilities of classical cryptography, post-quantum cryptography, and quantum-resistant cryptographic solutions\n - [View full report](examples/Quantum_Computing_Impact_on_Cryptography.md)\n\n9. **Cristiano Ronaldo's Performance Highlights** - Analysis of Cristiano Ronaldo's performance highlights\n - Discusses his career achievements, international goals, and performance in various matches\n - [View full report](examples/Cristiano_Ronaldo's_Performance_Highlights.md)\n\nTo run these examples or create your own research reports, you can use the following commands:\n\n```bash\n# Run with a specific query\nuv run main.py \"What factors are influencing AI adoption in healthcare?\"\n\n# Run with custom planning parameters\nuv run main.py --max_plan_iterations 3 \"How does quantum computing impact cryptography?\"\n\n# Run in interactive mode with built-in questions\nuv run main.py --interactive\n\n# Or run with basic interactive prompt\nuv run main.py\n\n# View all available options\nuv run main.py --help\n```\n\n### Interactive Mode\n\nThe application now supports an interactive mode with built-in questions in both English and Chinese:\n\n1. Launch the interactive mode:\n\n ```bash\n uv run main.py --interactive\n ```\n\n2. Select your preferred language (English or 中文)\n\n3. Choose from a list of built-in questions or select the option to ask your own question\n\n4. The system will process your question and generate a comprehensive research report\n\n### Human in the Loop\n\nDeerFlow includes a human in the loop mechanism that allows you to review, edit, and approve research plans before they are executed:\n\n1. **Plan Review**: When human in the loop is enabled, the system will present the generated research plan for your review before execution\n\n2. **Providing Feedback**: You can:\n\n - Accept the plan by responding with `[ACCEPTED]`\n - Edit the plan by providing feedback (e.g., `[EDIT PLAN] Add more steps about technical implementation`)\n - The system will incorporate your feedback and generate a revised plan\n\n3. **Auto-acceptance**: You can enable auto-acceptance to skip the review process:\n\n - Via API: Set `auto_accepted_plan: true` in your request\n\n4. **API Integration**: When using the API, you can provide feedback through the `feedback` parameter:\n\n ```json\n {\n \"messages\": [{ \"role\": \"user\", \"content\": \"What is quantum computing?\" }],\n \"thread_id\": \"my_thread_id\",\n \"auto_accepted_plan\": false,\n \"feedback\": \"[EDIT PLAN] Include more about quantum algorithms\"\n }\n ```\n\n### Command Line Arguments\n\nThe application supports several command-line arguments to customize its behavior:\n\n- **query**: The research query to process (can be multiple words)\n- **--interactive**: Run in interactive mode with built-in questions\n- **--max_plan_iterations**: Maximum number of planning cycles (default: 1)\n- **--max_step_num**: Maximum number of steps in a research plan (default: 3)\n- **--debug**: Enable detailed debug logging\n\n## FAQ\n\nPlease refer to the [FAQ.md](docs/FAQ.md) for more details.\n\n## License\n\nThis project is open source and available under the [MIT License](./LICENSE).\n\n## Acknowledgments\n\nDeerFlow is built upon the incredible work of the open-source community. We are deeply grateful to all the projects and contributors whose efforts have made DeerFlow possible. Truly, we stand on the shoulders of giants.\n\nWe would like to extend our sincere appreciation to the following projects for their invaluable contributions:\n\n- **[LangChain](https://github.com/langchain-ai/langchain)**: Their exceptional framework powers our LLM interactions and chains, enabling seamless integration and functionality.\n- **[LangGraph](https://github.com/langchain-ai/langgraph)**: Their innovative approach to multi-agent orchestration has been instrumental in enabling DeerFlow's sophisticated workflows.\n- **[Novel](https://github.com/steven-tey/novel)**: Their Notion-style WYSIWYG editor supports our report editing and AI-assisted rewriting.\n- **[RAGFlow](https://github.com/infiniflow/ragflow)**: We have achieved support for research on users' private knowledge bases through integration with RAGFlow.\n\nThese projects exemplify the transformative power of open-source collaboration, and we are proud to build upon their foundations.\n\n### Key Contributors\n\nA heartfelt thank you goes out to the core authors of `DeerFlow`, whose vision, passion, and dedication have brought this project to life:\n\n- **[Daniel Walnut](https://github.com/hetaoBackend/)**\n- **[Henry Li](https://github.com/magiccube/)**\n\nYour unwavering commitment and expertise have been the driving force behind DeerFlow's success. We are honored to have you at the helm of this journey.\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=bytedance/deer-flow&type=Date)](https://star-history.com/#bytedance/deer-flow&Date)", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "1568942a-e8ff-406e-a96d-0c2fd5da076a", "tool_call_id": "call_semgkgyfsd7f76uzwzgk3ja9", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to analyze the repository structure and get more details. Let me get the tree structure." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1713-bdb0-7342-923b-a62584dbcb8a", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "in_progress" }, { "content": "Research DeerFlow project overview and purpose", "status": "pending" }, { "content": "Investigate technical architecture and features", "status": "pending" }, { "content": "Analyze community activity and contributors", "status": "pending" }, { "content": "Research timeline and development history", "status": "pending" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_zcz13oewafi1i6ta6huoujl6", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'in_progress'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'pending'}, {'content': 'Investigate technical architecture and features', 'status': 'pending'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "07fdf373-5a9d-49ff-bb5b-0bf0104662f2", "tool_call_id": "call_zcz13oewafi1i6ta6huoujl6", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to analyze the repository structure and languages. Let me get more detailed information from GitHub API." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1713-e9ca-75a2-969c-a63281ae5d6e", "tool_calls": [ { "name": "bash", "args": { "description": "Get repository tree structure to understand organization", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow tree" }, "id": "call_8242yht1u7udvgn7a0q5t3oz", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Error: 404 Client Error: Not Found for url: https://api.github.com/repos/bytedance/deer-flow/git/trees/master?recursive=1", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "1ee29d42-4393-448a-971b-6ab8f2468955", "tool_call_id": "call_8242yht1u7udvgn7a0q5t3oz", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Let me try with the correct branch name. From the summary, I see the default branch is \"main\". Let me try that." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-0feb-7fd0-b86f-39c2cdb245c3", "tool_calls": [ { "name": "bash", "args": { "description": "Get repository tree structure using main branch", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow tree main" }, "id": "call_0ddx0pqlqtjwf24iat5ulbfd", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": ".dockerignore\n.env.example\n.github/\n copilot-instructions.md\n workflows/\n container.yaml\n lint.yaml\n unittest.yaml\n.gitignore\n.python-version\n.vscode/\n launch.json\n settings.json\nAgent.md\nCONTRIBUTING\nDockerfile\nLICENSE\nMakefile\nREADME.md\nREADME_de.md\nREADME_es.md\nREADME_ja.md\nREADME_pt.md\nREADME_ru.md\nREADME_zh.md\nSECURITY.md\nassets/\n architecture.png\nbootstrap.bat\nbootstrap.sh\nconf.yaml.example\ndocker-compose.yml\ndocs/\n API.md\n DEBUGGING.md\n FAQ.md\n configuration_guide.md\n mcp_integrations.md\n openapi.json\nexamples/\n AI_adoption_in_healthcare.md\n Cristiano_Ronaldo's_Performance_Highlights.md\n Quantum_Computing_Impact_on_Cryptography.md\n bitcoin_price_fluctuation.md\n how_to_use_claude_deep_research.md\n nanjing_tangbao.md\n openai_sora_report.md\n what_is_agent_to_agent_protocol.md\n what_is_llm.md\n what_is_mcp.md\nlanggraph.json\nmain.py\npre-commit\npyproject.toml\nserver.py\nsrc/\n __init__.py\n agents/\n __init__.py\n agents.py\n tool_interceptor.py\n citations/\n __init__.py\n collector.py\n extractor.py\n formatter.py\n models.py\n config/\n __init__.py\n agents.py\n configuration.py\n loader.py\n questions.py\n report_style.py\n tools.py\n crawler/\n __init__.py\n article.py\n crawler.py\n infoquest_client.py\n jina_client.py\n readability_extractor.py\n eval/\n __init__.py\n evaluator.py\n llm_judge.py\n metrics.py\n graph/\n __init__.py\n builder.py\n checkpoint.py\n nodes.py\n types.py\n utils.py\n llms/\n __init__.py\n llm.py\n providers/\n podcast/\n graph/", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "6d4dbb10-68e4-479b-a44c-235c8a1dbbb6", "tool_call_id": "call_0ddx0pqlqtjwf24iat5ulbfd", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to get more information about the repository. Let me get the languages breakdown and then start researching the project. First, I'll complete the current todo and move to research." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-3040-7213-aa0c-d2c708e6f30a", "tool_calls": [ { "name": "bash", "args": { "description": "Get detailed languages breakdown", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow languages" }, "id": "call_bjksa2s1umbkxcsboirhnuyd", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "{\n \"Python\": 1292574,\n \"TypeScript\": 503143,\n \"CSS\": 15128,\n \"JavaScript\": 7906,\n \"Dockerfile\": 2197,\n \"Makefile\": 1352,\n \"Shell\": 1152,\n \"Batchfile\": 497\n}", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "9ba4d979-f080-4d71-ba32-a21566dd1963", "tool_call_id": "call_bjksa2s1umbkxcsboirhnuyd", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to start the research phase. Let me begin with web searches to understand the project better. First, I'll search for DeerFlow overview and then dive deeper." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-4fe4-7081-96d1-3924234f311f", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "in_progress" }, { "content": "Investigate technical architecture and features", "status": "pending" }, { "content": "Analyze community activity and contributors", "status": "pending" }, { "content": "Research timeline and development history", "status": "pending" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_6jo3x6qwzw6sgneczzem8o97", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'in_progress'}, {'content': 'Investigate technical architecture and features', 'status': 'pending'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "5b5482a7-3411-4f4e-96c8-662613afa062", "tool_call_id": "call_6jo3x6qwzw6sgneczzem8o97", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to research DeerFlow project overview and purpose. Let me start with web searches to understand the project better. First, I'll search for general information about DeerFlow." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-76ef-76b1-9d4b-a3bb566bf817", "tool_calls": [ { "name": "web_search", "args": { "query": "DeerFlow bytedance deep research framework" }, "id": "call_hgpz1sygmlmflx6f326qc8tp", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"title\": \"Create Your Own Deep Research Agent with DeerFlow\",\n \"url\": \"https://thesequence.substack.com/p/the-sequence-engineering-661-create\",\n \"snippet\": \"DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source multi-agent research automation framework developed by ByteDance.\"\n },\n {\n \"title\": \"ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)\",\n \"url\": \"https://www.youtube.com/watch?v=Ui0ovCVDYGs\",\n \"snippet\": \"ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)\\nBijan Bowen\\n40600 subscribers\\n460 likes\\n14105 views\\n13 May 2025\\nTimestamps:\\n\\n00:00 - Intro\\n01:07 - First Look\\n02:53 - Local Test\\n05:00 - Second Test\\n08:55 - Generated Report\\n10:10 - Additional Info\\n11:21 - Local Install Tips\\n15:57 - Closing Thoughts\\n\\nIf you're a business looking to integrate AI visit https://bijanbowen.com to book a consultation.\\n\\nIn this video, we take a first look at the newly released DeerFlow repository from ByteDance. DeerFlow is a feature-rich, open-source deep research assistant that uses a local LLM to generate detailed, source-cited research reports on nearly any topic. Once deployed, it can search the web, pull from credible sources, and produce a well-structured report for the user to review.\\n\\nIn addition to its core research functionality, DeerFlow includes support for MCP server integration, a built-in coder agent that can run and test Python code, and even utilities to convert generated reports into formats like PowerPoint presentations or audio podcasts. The system is highly modular and is designed to be flexible enough for serious research tasks while remaining accessible to run locally.\\n\\nIn this video, we walk through a functional demo, test its capabilities across multiple prompts, and review the output it generates. We also explore a few installation tips, discuss how it integrates with local LLMs, and share some thoughts on how this kind of tool might evolve for research-heavy workflows or automation pipelines.\\n\\nGithub Repo: https://github.com/bytedance/deer-flow\\n98 comments\\n\"\n },\n {\n \"title\": \"Navigating the Landscape of Deep Research Frameworks - Oreate AI\",\n \"url\": \"https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks-a-comprehensive-comparison/0dc13e48eb8c756650112842c8d1a184\",\n \"snippet\": \"HomeContentNavigating the Landscape of Deep Research Frameworks: A Comprehensive Comparison. # Navigating the Landscape of Deep Research Frameworks: A Comprehensive Comparison. In recent years, the emergence of deep research frameworks has transformed how we approach complex inquiries. Let's explore six standout frameworks specifically optimized for deep research: DeerFlow by ByteDance, OpenDeepResearch from HuggingFace and LangChain, DeepResearchAgent by SkyworkAI, AutoDeepResearch from HKUDS, and Researcher developed by zhu-minjun. LangChain's OpenDeepResearch is another noteworthy contender that integrates reflection capabilities within its architecture; however, it holds a lower star count at 4.3k compared to others in our lineup. Lastly, Researcher brings forth unique elements such as CycleReviewer aimed at enhancing peer review processes but remains less popular among users given its modest star count of just 0.2k on GitHub. The core principles outlined by OpenAI serve as foundational guidelines across these frameworks: break down complex tasks into manageable parts using a three-step process—Plan -> Execute -> Synthesize—to maximize efficiency while minimizing costs associated with API usage during extensive research endeavors.\"\n },\n {\n \"title\": \"ByteDance DeerFlow: Multi AI Agent framework for Deep ...\",\n \"url\": \"https://medium.com/data-science-in-your-pocket/bytedance-deerflow-multi-ai-agent-framework-for-deep-research-acfbc4d90fbd\",\n \"snippet\": \"A community-driven multi-agent research framework. It combines language models, search engines, web crawlers, and text-to-speech features to automate deep\"\n },\n {\n \"title\": \"ByteDance Open-Sources DeerFlow: A Modular Multi-Agent ... - Reddit\",\n \"url\": \"https://www.reddit.com/r/machinelearningnews/comments/1kj3in1/bytedance_opensources_deerflow_a_modular/\",\n \"snippet\": \"ByteDance has open-sourced DeerFlow, a modular multi-agent framework built on LangChain and LangGraph to streamline complex research workflows.\"\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_search", "id": "4b74cdff-f918-42a1-ad1d-c8263254d184", "tool_call_id": "call_hgpz1sygmlmflx6f326qc8tp", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-8ec5-7981-bda6-a41abac2fb9b", "tool_calls": [ { "name": "web_fetch", "args": { "url": "https://thesequence.substack.com/p/the-sequence-engineering-661-create" }, "id": "call_t01ba41is01zr7fksmio9uju", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "# The Sequence Engineering #661: Create Your Own Deep Research Agent with DeerFlow\n\n[![TheSequence](https://substackcdn.com/image/fetch/$s_!t4FH!,w_40,h_40,c_fill,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F7c763928-9762-43a0-a55f-9ee9040fa6e1_210x210.png)](https://thesequence.substack.com/)\n\n# [TheSequence](https://thesequence.substack.com/)\n\nSubscribeSign in\n\n# The Sequence Engineering \\#661: Create Your Own Deep Research Agent with DeerFlow\n\n### The frameworks allows the creation of end-to-end research workflows.\n\nJun 11, 2025\n\n∙ Paid\n\n17\n\nShare\n\n[![Generated image](https://substackcdn.com/image/fetch/$s_!7eiP!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e659a3c-cf66-40ee-9d86-dd8ff2167881_1536x1024.png)](https://substackcdn.com/image/fetch/$s_!7eiP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e659a3c-cf66-40ee-9d86-dd8ff2167881_1536x1024.png) Created Using GPT-4o\n\n[DeerFlow (Deep Exploration and Efficient Research Flow)](https://deerflow.tech/) is an open-source multi-agent research automation framework developed by ByteDance and released under the MIT license in 2025. Designed to address the increasing demand for scalable, auditable, and extensible research workflows, DeerFlow goes beyond the conventional single-agent LLM wrappers. It implements a graph-based orchestration of specialized agents that automate research pipelines end-to-end. Whether the task involves web search, data analysis, report generation, or podcast creation, DeerFlow delivers structured and multimodal outputs with minimal human intervention. This essay explores DeerFlow's architectural underpinnings, key capabilities, and use cases, offering a technical perspective ideal for AI developers, research engineers, and MLOps practitioners.\n\n## **1\\. Architectural Overview**\n\n## This post is for paid subscribers\n\n[Subscribe](https://thesequence.substack.com/subscribe?simple=true&next=https%3A%2F%2Fthesequence.substack.com%2Fp%2Fthe-sequence-engineering-661-create&utm_source=paywall&utm_medium=web&utm_content=165620307)\n\n[Already a paid subscriber? **Sign in**](https://substack.com/sign-in?redirect=%2Fp%2Fthe-sequence-engineering-661-create&for_pub=thesequence&change_user=false)", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_fetch", "id": "15217f79-cc31-4db1-b9be-7d6d7c1020bb", "tool_call_id": "call_t01ba41is01zr7fksmio9uju", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to search for more information about DeerFlow's technical details and features. Let me search for more comprehensive information." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-aa32-7550-8bce-4eb5e486db9d", "tool_calls": [ { "name": "web_search", "args": { "query": "DeerFlow architecture multi-agent LangGraph research framework" }, "id": "call_bsh4c16e3tbovbf0mfy48xsp", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqingsong/deer-flow\",\n \"snippet\": \"DeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis. ... DeerFlow uses LangGraph for its workflow\"\n },\n {\n \"title\": \"DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep ...\",\n \"url\": \"https://www.linkedin.com/pulse/deerflow-modular-multi-agent-framework-deep-research-ramichetty-pbhxc\",\n \"snippet\": \"# DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep Research Automation. Released under the MIT license, DeerFlow empowers developers and researchers to automate complex workflows, from academic research to enterprise-grade data analysis. DeerFlow overcomes this limitation through a multi-agent architecture, where each agent specializes in a distinct function, such as task planning, knowledge retrieval, code execution, or report generation. This architecture ensures that DeerFlow can handle diverse research scenarios, such as synthesizing literature reviews, generating data visualizations, or drafting multimodal content. These integrations make DeerFlow a powerful tool for research analysts, data scientists, and technical writers seeking to combine reasoning, execution, and content creation in a single platform. DeerFlow represents a significant advancement in research automation, combining the power of multi-agent coordination, LLM-driven reasoning, and human-in-the-loop collaboration. Its modular architecture, deep tool integrations, and developer-friendly design make it a compelling choice for researchers and organizations seeking to accelerate complex workflows.\"\n },\n {\n \"title\": \"DeerFlow: Multi-Agent AI For Research Automation 2025 - FireXCore\",\n \"url\": \"https://firexcore.com/blog/what-is-deerflow/\",\n \"snippet\": \"What is DeerFlow? DeerFlow is an open-source multi-agent AI framework for automating complex research tasks, built on LangChain and LangGraph.\"\n },\n {\n \"title\": \"DeerFlow: A Game-Changer for Automated Research and Content ...\",\n \"url\": \"https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a\",\n \"snippet\": \"# DeerFlow: A Game-Changer for Automated Research and Content Creation. How this open-source multi-agent framework is revolutionizing the way we conduct research and generate content. Picture this: You need a comprehensive research report on quantum computing, cryptocurrency market trends, or the latest AI developments. Instead of spending days gathering information, analyzing data, and writing a structured report, you simply input your research topic and let an intelligent system handle the entire process for you. As someone who’s spent weeks investigating AI research tools, I can confidently say that DeerFlow represents one of the most impressive open-source implementations of a multi-agent research system I’ve encountered. ## What Makes DeerFlow Special? At its core, DeerFlow (Deep Exploration and Efficient Research Flow) is a community-driven framework that combines the power of language models with specialized tools for tasks like web searching, content crawling, and even Python code execution. But what truly sets it apart is its thoughtfully designed multi-agent architecture. > “DeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis.\"\n },\n {\n \"title\": \"ByteDance Open-Sources DeerFlow: A Modular Multi-Agent ... - Reddit\",\n \"url\": \"https://www.reddit.com/r/machinelearningnews/comments/1kj3in1/bytedance_opensources_deerflow_a_modular/\",\n \"snippet\": \"ByteDance has open-sourced DeerFlow, a modular multi-agent framework built on LangChain and LangGraph to streamline complex research workflows.\"\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_search", "id": "cbe52f9c-f68b-470f-9243-99d10e3b04f4", "tool_call_id": "call_bsh4c16e3tbovbf0mfy48xsp", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-c53a-72b2-9b2b-61c1a21e0fa8", "tool_calls": [ { "name": "web_fetch", "args": { "url": "https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a" }, "id": "call_e91r6sqp57hjufu0jh10ejw2", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "# DeerFlow: A Game-Changer for Automated Research and Content Creation | by heavendai | Medium\n\n[Sitemap](https://medium.com/sitemap/sitemap.xml)\n\n[Open in app](https://play.google.com/store/apps/details?id=com.medium.reader&referrer=utm_source%3DmobileNavBar&source=post_page---top_nav_layout_nav-----------------------------------------)\n\nSign up\n\n[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40mingyang.heaven%2Fdeerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)\n\n[Medium Logo](https://medium.com/?source=post_page---top_nav_layout_nav-----------------------------------------)\n\n[Write](https://medium.com/m/signin?operation=register&redirect=https%3A%2F%2Fmedium.com%2Fnew-story&source=---top_nav_layout_nav-----------------------new_post_topnav------------------)\n\n[Search](https://medium.com/search?source=post_page---top_nav_layout_nav-----------------------------------------)\n\nSign up\n\n[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40mingyang.heaven%2Fdeerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)\n\n![](https://miro.medium.com/v2/resize:fill:32:32/1*dmbNkD5D-u45r44go_cf0g.png)\n\nMember-only story\n\n# DeerFlow: A Game-Changer for Automated Research and Content Creation\n\n[![heavendai](https://miro.medium.com/v2/resize:fill:32:32/1*IXhhjFGdOYuesKUi21mM-w.png)](https://medium.com/@mingyang.heaven?source=post_page---byline--83612f683e7a---------------------------------------)\n\n[heavendai](https://medium.com/@mingyang.heaven?source=post_page---byline--83612f683e7a---------------------------------------)\n\n5 min read\n\n·\n\nMay 10, 2025\n\n--\n\nShare\n\nHow this open-source multi-agent framework is revolutionizing the way we conduct research and generate content\n\nPicture this: You need a comprehensive research report on quantum computing, cryptocurrency market trends, or the latest AI developments. Instead of spending days gathering information, analyzing data, and writing a structured report, you simply input your research topic and let an intelligent system handle the entire process for you.\n\nThis isn’t science fiction — it’s the reality of what [DeerFlow](https://deerflow.tech/) brings to the table. As someone who’s spent weeks investigating AI research tools, I can confidently say that DeerFlow represents one of the most impressive open-source implementations of a multi-agent research system I’ve encountered.\n\nPress enter or click to view image in full size\n\n![](https://miro.medium.com/v2/resize:fit:700/0*z6AflZMIrPEgP7Un.png)\n\nDeerFlow’s modular multi-agent architecture\n\n## What Makes DeerFlow Special?\n\nAt its core, DeerFlow (Deep Exploration and Efficient Research Flow) is a community-driven framework that combines the power of language models with specialized tools for tasks like web searching, content crawling, and even Python code execution. But what truly sets it apart is its thoughtfully designed multi-agent architecture.\n\n> “DeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis. The system is built on LangGraph, enabling a flexible state-based workflow where components communicate through a well-defined message passing system.”\n\nRather than relying on a single large language model to handle everything, DeerFlow breaks down the research process into manageable phases, each handled by specialized AI agents:\n\n- **Coordinator**: The entry point that manages the workflow lifecycle, initiating the research process and delegating tasks.\n- **Planner**: The strategic component that analyzes research objectives and creates structured execution plans.\n- **Research Team**: A collection of specialized agents including a Researcher (for web searches and information gathering) and a Coder (for handling technical tasks).\n- **Reporter**: The final stage processor that aggregates findings and generates comprehensive research reports.\n\n[![heavendai](https://mi", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_fetch", "id": "9ee06fbe-aabc-4c8e-b437-19241597eb36", "tool_call_id": "call_e91r6sqp57hjufu0jh10ejw2", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to research more about DeerFlow's technical architecture and features. Let me continue with web searches." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-e574-7b10-8918-7804a5b4b879", "tool_calls": [ { "name": "web_search", "args": { "query": "DeerFlow features web search crawling MCP integration" }, "id": "call_hpyb8pfq0jkykts3xxhw28vx", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqingsong/deer-flow\",\n \"snippet\": \"In this demo, we showcase how to use DeerFlow to: Seamlessly integrate with MCP services; Conduct the Deep Research process and produce a comprehensive report\"\n },\n {\n \"title\": \"DeerFlow: Multi-Agent AI For Research Automation 2025 - FireXCore\",\n \"url\": \"https://firexcore.com/blog/what-is-deerflow/\",\n \"snippet\": \"Web Search & Crawling: Pulls real-time data from external sources ... MCP Integration: Connects with ByteDance's internal Model Control\"\n },\n {\n \"title\": \"bytedance/deer-flow: DeerFlow is a community-driven framework for ...\",\n \"url\": \"https://app.daily.dev/posts/bytedance-deer-flow-deerflow-is-a-community-driven-framework-for-deep-research-combining-language--mzmdyvbbj\",\n \"snippet\": \"# bytedance/deer-flow: DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the op. DeerFlow is an open-source research framework combining language models with tools like web search, crawling, and Python execution. It integrates with multiple MCP services, supports human-in-the-loop collaboration, and has both console and web UI options. Installation requires Python 3.12+, Node.js, and tools such as uv and. •12m read time• From github.com. Demo📑 Table of ContentsQuick StartSupported Search EnginesFeaturesArchitectureText-to-Speech IntegrationDevelopmentExamplesFAQLicenseAcknowledgmentsStar History.\"\n },\n {\n \"title\": \"DeerFlow\",\n \"url\": \"https://deerflow.tech/\",\n \"snippet\": \"Meet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant\"\n },\n {\n \"title\": \"ByteDance Opens Source Deep Research Framework DeerFlow\",\n \"url\": \"https://news.aibase.com/news/17928\",\n \"snippet\": \"Integration of Multiple Tools: Supports web search, Arxiv academic resource retrieval, crawling, and Python code execution, providing strong\"\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_search", "id": "4415f97a-aeb3-41a5-8144-bccf4f6b5c2c", "tool_call_id": "call_hpyb8pfq0jkykts3xxhw28vx", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to understand the technical architecture better and research the community activity. Let me fetch more information." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1714-fde8-7d41-8522-bcb8a0babbe5", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "in_progress" }, { "content": "Analyze community activity and contributors", "status": "pending" }, { "content": "Research timeline and development history", "status": "pending" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_u1sf1unbxq5x2jr4eqtyei4q", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'completed'}, {'content': 'Investigate technical architecture and features', 'status': 'in_progress'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "cdedc62b-b03d-4d3e-9fdf-8812080018f8", "tool_call_id": "call_u1sf1unbxq5x2jr4eqtyei4q", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1715-2150-7083-a453-656344486f9d", "tool_calls": [ { "name": "web_fetch", "args": { "url": "https://deerflow.tech/" }, "id": "call_13utybv555uqnm2ijodwli3d", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "# 🦌 DeerFlow\n\n# Deep Researchat Your Fingertipsat Your Fingertips\n\nMeet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant insights, comprehensive reports, and even captivating podcasts.\n\n[Get Started](https://github.com/bytedance/deer-flow)\n\n\\\\* DEER stands for Deep Exploration and Efficient Research.\n\n## Case Studies\n\nSee DeerFlow in action through replays.\n\n[**How tall is Eiffel Tower compared to tallest building?** \\\\\nThe research compares the heights and global significance of the Eiffel Tower and Burj Khalifa, and uses Python code to calculate the multiples.](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)\n\n[**What are the top trending repositories on GitHub?** \\\\\nThe research utilized MCP services to identify the most popular GitHub repositories and documented them in detail using search engines.](https://deerflow.tech/chat?replay=github-top-trending-repo)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=github-top-trending-repo)\n\n[**Write an article about Nanjing's traditional dishes** \\\\\nThe study vividly showcases Nanjing's famous dishes through rich content and imagery, uncovering their hidden histories and cultural significance.](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)\n\n[**How to decorate a small rental apartment?** \\\\\nThe study provides readers with practical and straightforward methods for decorating apartments, accompanied by inspiring images.](https://deerflow.tech/chat?replay=rental-apartment-decoration)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=rental-apartment-decoration)\n\n[**Introduce the movie 'Léon: The Professional'** \\\\\nThe research provides a comprehensive introduction to the movie 'Léon: The Professional', including its plot, characters, and themes.](https://deerflow.tech/chat?replay=review-of-the-professional)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=review-of-the-professional)\n\n[**How do you view the takeaway war in China? (in Chinese)** \\\\\nThe research analyzes the intensifying competition between JD and Meituan, highlighting their strategies, technological innovations, and challenges.](https://deerflow.tech/chat?replay=china-food-delivery)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=china-food-delivery)\n\n[**Are ultra-processed foods linked to health?** \\\\\nThe research examines the health risks of rising ultra-processed food consumption, urging more research on long-term effects and individual differences.](https://deerflow.tech/chat?replay=ultra-processed-foods)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=ultra-processed-foods)\n\n[**Write an article on \"Would you insure your AI twin?\"** \\\\\nThe research explores the concept of insuring AI twins, highlighting their benefits, risks, ethical considerations, and the evolving regulatory.](https://deerflow.tech/chat?replay=ai-twin-insurance)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=ai-twin-insurance)\n\n## Multi-Agent Architecture\n\nExperience the agent teamwork with our Supervisor + Handoffs design pattern.\n\nStart\n\nCoordinator\n\nPlanner\n\nReporter\n\nHuman Feedback\n\nResearch Team\n\nResearcher\n\nCoder\n\nEnd\n\nPress enter or space to select a node.You can then use the arrow keys to move the node around. Press delete to remove it and escape to cancel.\n\nPress enter or space to select an edge. You can then press delete to remove it or escape to cancel.\n\n## Core Features\n\nFind out what makes DeerFlow effective.\n\n[**Dive Deeper and Reach Wider** \\\\\nUnlock deeper insights with advanced tools. Our powerful search + crawling and Python tools gathers comprehensive data, delivering in-depth reports to enhance your study.](https://github.com/bytedance/deer-flow/blob/main/src/tools)\n\n[Learn more](https://github.com/bytedance/deer-flow/blob/main/src/tools)\n\n[**Human-in-the-loop** \\\\", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_fetch", "id": "bb556bbf-840f-4ca6-937d-0a81915ae961", "tool_call_id": "call_13utybv555uqnm2ijodwli3d", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to investigate the technical architecture and features more deeply. Let me also check the community activity and contributors." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1715-3e60-70d2-9785-6c969132a27d", "tool_calls": [ { "name": "bash", "args": { "description": "Get contributors information", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow contributors" }, "id": "call_s3lcjnzqz4x40wuii753a4yl", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"login\": \"henry-byted\",\n \"id\": 209858577,\n \"node_id\": \"U_kgDODIIwEQ\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/209858577?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/henry-byted\",\n \"html_url\": \"https://github.com/henry-byted\",\n \"followers_url\": \"https://api.github.com/users/henry-byted/followers\",\n \"following_url\": \"https://api.github.com/users/henry-byted/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/henry-byted/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/henry-byted/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/henry-byted/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/henry-byted/orgs\",\n \"repos_url\": \"https://api.github.com/users/henry-byted/repos\",\n \"events_url\": \"https://api.github.com/users/henry-byted/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/henry-byted/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 203\n },\n {\n \"login\": \"WillemJiang\",\n \"id\": 219644,\n \"node_id\": \"MDQ6VXNlcjIxOTY0NA==\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/219644?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/WillemJiang\",\n \"html_url\": \"https://github.com/WillemJiang\",\n \"followers_url\": \"https://api.github.com/users/WillemJiang/followers\",\n \"following_url\": \"https://api.github.com/users/WillemJiang/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/WillemJiang/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/WillemJiang/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/WillemJiang/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/WillemJiang/orgs\",\n \"repos_url\": \"https://api.github.com/users/WillemJiang/repos\",\n \"events_url\": \"https://api.github.com/users/WillemJiang/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/WillemJiang/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 130\n },\n {\n \"login\": \"hetaoBackend\",\n \"id\": 45447813,\n \"node_id\": \"MDQ6VXNlcjQ1NDQ3ODEz\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/45447813?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/hetaoBackend\",\n \"html_url\": \"https://github.com/hetaoBackend\",\n \"followers_url\": \"https://api.github.com/users/hetaoBackend/followers\",\n \"following_url\": \"https://api.github.com/users/hetaoBackend/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/hetaoBackend/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/hetaoBackend/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/hetaoBackend/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/hetaoBackend/orgs\",\n \"repos_url\": \"https://api.github.com/users/hetaoBackend/repos\",\n \"events_url\": \"https://api.github.com/users/hetaoBackend/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/hetaoBackend/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 25\n },\n {\n \"login\": \"forx11\",\n \"id\": 210814561,\n \"node_id\": \"U_kgDODJDGYQ\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/210814561?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/forx11\",\n \"html_url\": \"https://github.com/forx11\",\n \"followers_url\": \"https://api.github.com/users/forx11/followers\",\n \"following_url\": \"https://api.github.com/users/forx11/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/forx11/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/forx11/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/forx11/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/forx11/orgs\",\n \"repos_url\": \"https://api.github.com/users/forx11/repos\",\n \"events_url\": \"https://api.github.com/users/forx11/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/forx11/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 14\n },\n {\n \"login\": \"foreleven\",\n \"id\": 4785594,\n \"node_id\": \"MDQ6VXNlcjQ3ODU1OTQ=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/4785594?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/foreleven\",\n \"html_url\": \"https://github.com/foreleven\",\n \"followers_url\": \"https://api.github.com/users/foreleven/followers\",\n \"following_url\": \"https://api.github.com/users/foreleven/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/foreleven/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/foreleven/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/foreleven/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/foreleven/orgs\",\n \"repos_url\": \"https://api.github.com/users/foreleven/repos\",\n \"events_url\": \"https://api.github.com/users/foreleven/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/foreleven/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 13\n },\n {\n \"login\": \"MagicCube\",\n \"id\": 1003147,\n \"node_id\": \"MDQ6VXNlcjEwMDMxNDc=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/1003147?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/MagicCube\",\n \"html_url\": \"https://github.com/MagicCube\",\n \"followers_url\": \"https://api.github.com/users/MagicCube/followers\",\n \"following_url\": \"https://api.github.com/users/MagicCube/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/MagicCube/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/MagicCube/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/MagicCube/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/MagicCube/orgs\",\n \"repos_url\": \"https://api.github.com/users/MagicCube/repos\",\n \"events_url\": \"https://api.github.com/users/MagicCube/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/MagicCube/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 12\n },\n {\n \"login\": \"dependabot[bot]\",\n \"id\": 49699333,\n \"node_id\": \"MDM6Qm90NDk2OTkzMzM=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/in/29110?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/dependabot%5Bbot%5D\",\n \"html_url\": \"https://github.com/apps/dependabot\",\n \"followers_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/followers\",\n \"following_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/orgs\",\n \"repos_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/repos\",\n \"events_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/received_events\",\n \"type\": \"Bot\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 10\n },\n {\n \"login\": \"leohxj\",\n \"id\": 1506900,\n \"node_id\": \"MDQ6VXNlcjE1MDY5MDA=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/1506900?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/leohxj\",\n \"html_url\": \"https://github.com/leohxj\",\n \"followers_url\": \"https://api.github.com/users/leohxj/followers\",\n \"following_url\": \"https://api.github.com/users/leohxj/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/leohxj/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/leohxj/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/leohxj/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/leohxj/orgs\",\n \"repos_url\": \"https://api.github.com/users/leohxj/repos\",\n \"events_url\": \"https://api.github.com/users/leohxj/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/leohxj/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 6\n },\n {\n \"login\": \"wanghao-6\",\n \"id\": 210654907,\n \"node_id\": \"U_kgDODI5Wuw\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/210654907?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/wanghao-6\",\n \"html_url\": \"https://github.com/wanghao-6\",\n \"followers_url\": \"https://api.github.com/users/wanghao-6/followers\",\n \"following_url\": \"https://api.github.com/users/wanghao-6/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/wanghao-6/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/wanghao-6/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/wanghao-6/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/wanghao-6/orgs\",\n \"repos_url\": \"https://api.github.com/users/wanghao-6/repos\",\n \"events_url\": \"https://api.github.com/users/wanghao-6/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/wanghao-6/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 6\n },\n {\n \"login\": \"xunliu\",\n \"id\": 3677382,\n \"node_id\": \"MDQ6VXNlcjM2NzczODI=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/3677382?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/xunliu\",\n \"html_url\": \"https://github.com/xunliu\",\n \"followers_url\": \"https://api.github.com/users/xunliu/followers\",\n \"following_url\": \"https://api.github.com/users/xunliu/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/xunliu/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/xunliu/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/xunliu/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/xunliu/orgs\",\n \"repos_url\": \"https://api.github.com/users/xunliu/repos\",\n \"events_url\": \"https://api.github.com/users/xunliu/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/xunliu/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 6\n },\n {\n \"login\": \"nonoroazoro-byte\",\n \"id\": 210655313,\n \"node_id\": \"U_kgDODI5YUQ\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/210655313?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/nonoroazoro-byte\",\n \"html_url\": \"https://github.com/nonoroazoro-byte\",\n \"followers_url\": \"https://api.github.com/users/nonoroazoro-byte/followers\",\n \"following_url\": \"https://api.github.com/users/nonoroazoro-byte/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/nonoroazoro-byte/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/nonoroazoro-byte/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/nonoroazoro-byte/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/nonoroazoro-byte/orgs\",\n \"repos_url\": \"https://api.github.com/users/nonoroazoro-byte/repos\",\n \"events_url\": \"https://api.github.com/users/nonoroazoro-byte/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/nonoroazoro-byte/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 6\n },\n {\n \"login\": \"blueberrycongee\",\n \"id\": 117764480,\n \"node_id\": \"U_kgDOBwTxgA\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/117764480?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/blueberrycongee\",\n \"html_url\": \"https://github.com/blueberrycongee\",\n \"followers_url\": \"https://api.github.com/users/blueberrycongee/followers\",\n \"following_url\": \"https://api.github.com/users/blueberrycongee/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/blueberrycongee/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/blueberrycongee/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/blueberrycongee/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/blueberrycongee/orgs\",\n \"repos_url\": \"https://api.github.com/users/blueberrycongee/repos\",\n \"events_url\": \"https://api.github.com/users/blueberrycongee/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/blueberrycongee/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 6\n },\n {\n \"login\": \"jimmyuconn1982\",\n \"id\": 234714353,\n \"node_id\": \"U_kgDODf108Q\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/234714353?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/jimmyuconn1982\",\n \"html_url\": \"https://github.com/jimmyuconn1982\",\n \"followers_url\": \"https://api.github.com/users/jimmyuconn1982/followers\",\n \"following_url\": \"https://api.github.com/users/jimmyuconn1982/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/jimmyuconn1982/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/jimmyuconn1982/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/jimmyuconn1982/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/jimmyuconn1982/orgs\",\n \"repos_url\": \"https://api.github.com/users/jimmyuconn1982/repos\",\n \"events_url\": \"https://api.github.com/users/jimmyuconn1982/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/jimmyuconn1982/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 5\n },\n {\n \"login\": \"HagonChan\",\n \"id\": 77165006,\n \"node_id\": \"MDQ6VXNlcjc3MTY1MDA2\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/77165006?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/HagonChan\",\n \"html_url\": \"https://github.com/HagonChan\",\n \"followers_url\": \"https://api.github.com/users/HagonChan/followers\",\n \"following_url\": \"https://api.github.com/users/HagonChan/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/HagonChan/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/us\n[... Observation truncated due to length ...]\nwing_url\": \"https://api.github.com/users/AffanShaikhsurab/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/AffanShaikhsurab/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/AffanShaikhsurab/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/AffanShaikhsurab/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/AffanShaikhsurab/orgs\",\n \"repos_url\": \"https://api.github.com/users/AffanShaikhsurab/repos\",\n \"events_url\": \"https://api.github.com/users/AffanShaikhsurab/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/AffanShaikhsurab/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"laundry2\",\n \"id\": 40748509,\n \"node_id\": \"MDQ6VXNlcjQwNzQ4NTA5\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/40748509?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/laundry2\",\n \"html_url\": \"https://github.com/laundry2\",\n \"followers_url\": \"https://api.github.com/users/laundry2/followers\",\n \"following_url\": \"https://api.github.com/users/laundry2/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/laundry2/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/laundry2/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/laundry2/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/laundry2/orgs\",\n \"repos_url\": \"https://api.github.com/users/laundry2/repos\",\n \"events_url\": \"https://api.github.com/users/laundry2/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/laundry2/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"orifake\",\n \"id\": 9210325,\n \"node_id\": \"MDQ6VXNlcjkyMTAzMjU=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/9210325?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/orifake\",\n \"html_url\": \"https://github.com/orifake\",\n \"followers_url\": \"https://api.github.com/users/orifake/followers\",\n \"following_url\": \"https://api.github.com/users/orifake/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/orifake/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/orifake/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/orifake/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/orifake/orgs\",\n \"repos_url\": \"https://api.github.com/users/orifake/repos\",\n \"events_url\": \"https://api.github.com/users/orifake/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/orifake/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"Dantence\",\n \"id\": 84451807,\n \"node_id\": \"MDQ6VXNlcjg0NDUxODA3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/84451807?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/Dantence\",\n \"html_url\": \"https://github.com/Dantence\",\n \"followers_url\": \"https://api.github.com/users/Dantence/followers\",\n \"following_url\": \"https://api.github.com/users/Dantence/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/Dantence/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/Dantence/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/Dantence/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/Dantence/orgs\",\n \"repos_url\": \"https://api.github.com/users/Dantence/repos\",\n \"events_url\": \"https://api.github.com/users/Dantence/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/Dantence/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"Abeautifulsnow\",\n \"id\": 28704977,\n \"node_id\": \"MDQ6VXNlcjI4NzA0OTc3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/28704977?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/Abeautifulsnow\",\n \"html_url\": \"https://github.com/Abeautifulsnow\",\n \"followers_url\": \"https://api.github.com/users/Abeautifulsnow/followers\",\n \"following_url\": \"https://api.github.com/users/Abeautifulsnow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/Abeautifulsnow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/Abeautifulsnow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/Abeautifulsnow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/Abeautifulsnow/orgs\",\n \"repos_url\": \"https://api.github.com/users/Abeautifulsnow/repos\",\n \"events_url\": \"https://api.github.com/users/Abeautifulsnow/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/Abeautifulsnow/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"yuehua-s\",\n \"id\": 41819795,\n \"node_id\": \"MDQ6VXNlcjQxODE5Nzk1\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/41819795?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/yuehua-s\",\n \"html_url\": \"https://github.com/yuehua-s\",\n \"followers_url\": \"https://api.github.com/users/yuehua-s/followers\",\n \"following_url\": \"https://api.github.com/users/yuehua-s/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/yuehua-s/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/yuehua-s/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/yuehua-s/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/yuehua-s/orgs\",\n \"repos_url\": \"https://api.github.com/users/yuehua-s/repos\",\n \"events_url\": \"https://api.github.com/users/yuehua-s/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/yuehua-s/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"jiaoqiyuan\",\n \"id\": 13357933,\n \"node_id\": \"MDQ6VXNlcjEzMzU3OTMz\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/13357933?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/jiaoqiyuan\",\n \"html_url\": \"https://github.com/jiaoqiyuan\",\n \"followers_url\": \"https://api.github.com/users/jiaoqiyuan/followers\",\n \"following_url\": \"https://api.github.com/users/jiaoqiyuan/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/jiaoqiyuan/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/jiaoqiyuan/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/jiaoqiyuan/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/jiaoqiyuan/orgs\",\n \"repos_url\": \"https://api.github.com/users/jiaoqiyuan/repos\",\n \"events_url\": \"https://api.github.com/users/jiaoqiyuan/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/jiaoqiyuan/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 3\n },\n {\n \"login\": \"loganaden\",\n \"id\": 1688420,\n \"node_id\": \"MDQ6VXNlcjE2ODg0MjA=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/1688420?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/loganaden\",\n \"html_url\": \"https://github.com/loganaden\",\n \"followers_url\": \"https://api.github.com/users/loganaden/followers\",\n \"following_url\": \"https://api.github.com/users/loganaden/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/loganaden/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/loganaden/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/loganaden/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/loganaden/orgs\",\n \"repos_url\": \"https://api.github.com/users/loganaden/repos\",\n \"events_url\": \"https://api.github.com/users/loganaden/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/loganaden/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n },\n {\n \"login\": \"voroq\",\n \"id\": 4570190,\n \"node_id\": \"MDQ6VXNlcjQ1NzAxOTA=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/4570190?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/voroq\",\n \"html_url\": \"https://github.com/voroq\",\n \"followers_url\": \"https://api.github.com/users/voroq/followers\",\n \"following_url\": \"https://api.github.com/users/voroq/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/voroq/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/voroq/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/voroq/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/voroq/orgs\",\n \"repos_url\": \"https://api.github.com/users/voroq/repos\",\n \"events_url\": \"https://api.github.com/users/voroq/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/voroq/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n },\n {\n \"login\": \"lele3436\",\n \"id\": 223808995,\n \"node_id\": \"U_kgDODVcN4w\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/223808995?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/lele3436\",\n \"html_url\": \"https://github.com/lele3436\",\n \"followers_url\": \"https://api.github.com/users/lele3436/followers\",\n \"following_url\": \"https://api.github.com/users/lele3436/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/lele3436/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/lele3436/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/lele3436/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/lele3436/orgs\",\n \"repos_url\": \"https://api.github.com/users/lele3436/repos\",\n \"events_url\": \"https://api.github.com/users/lele3436/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/lele3436/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n },\n {\n \"login\": \"johnny0120\",\n \"id\": 15564476,\n \"node_id\": \"MDQ6VXNlcjE1NTY0NDc2\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/15564476?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/johnny0120\",\n \"html_url\": \"https://github.com/johnny0120\",\n \"followers_url\": \"https://api.github.com/users/johnny0120/followers\",\n \"following_url\": \"https://api.github.com/users/johnny0120/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/johnny0120/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/johnny0120/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/johnny0120/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/johnny0120/orgs\",\n \"repos_url\": \"https://api.github.com/users/johnny0120/repos\",\n \"events_url\": \"https://api.github.com/users/johnny0120/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/johnny0120/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n },\n {\n \"login\": \"infoquest-byteplus\",\n \"id\": 243287575,\n \"node_id\": \"U_kgDODoBGFw\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/243287575?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/infoquest-byteplus\",\n \"html_url\": \"https://github.com/infoquest-byteplus\",\n \"followers_url\": \"https://api.github.com/users/infoquest-byteplus/followers\",\n \"following_url\": \"https://api.github.com/users/infoquest-byteplus/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/infoquest-byteplus/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/infoquest-byteplus/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/infoquest-byteplus/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/infoquest-byteplus/orgs\",\n \"repos_url\": \"https://api.github.com/users/infoquest-byteplus/repos\",\n \"events_url\": \"https://api.github.com/users/infoquest-byteplus/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/infoquest-byteplus/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n },\n {\n \"login\": \"Bin1783\",\n \"id\": 54528024,\n \"node_id\": \"MDQ6VXNlcjU0NTI4MDI0\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/54528024?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/Bin1783\",\n \"html_url\": \"https://github.com/Bin1783\",\n \"followers_url\": \"https://api.github.com/users/Bin1783/followers\",\n \"following_url\": \"https://api.github.com/users/Bin1783/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/Bin1783/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/Bin1783/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/Bin1783/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/Bin1783/orgs\",\n \"repos_url\": \"https://api.github.com/users/Bin1783/repos\",\n \"events_url\": \"https://api.github.com/users/Bin1783/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/Bin1783/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n },\n {\n \"login\": \"XingLiu0923\",\n \"id\": 32811666,\n \"node_id\": \"MDQ6VXNlcjMyODExNjY2\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/32811666?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/XingLiu0923\",\n \"html_url\": \"https://github.com/XingLiu0923\",\n \"followers_url\": \"https://api.github.com/users/XingLiu0923/followers\",\n \"following_url\": \"https://api.github.com/users/XingLiu0923/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/XingLiu0923/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/XingLiu0923/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/XingLiu0923/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/XingLiu0923/orgs\",\n \"repos_url\": \"https://api.github.com/users/XingLiu0923/repos\",\n \"events_url\": \"https://api.github.com/users/XingLiu0923/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/XingLiu0923/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false,\n \"contributions\": 2\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "ede540fe-b1fc-42e2-8617-84092799669a", "tool_call_id": "call_s3lcjnzqz4x40wuii753a4yl", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1715-67d2-7933-8acd-c67740111988", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "completed" }, { "content": "Analyze community activity and contributors", "status": "in_progress" }, { "content": "Research timeline and development history", "status": "pending" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_tngiymm5i7ov5dubodstet59", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'completed'}, {'content': 'Investigate technical architecture and features', 'status': 'completed'}, {'content': 'Analyze community activity and contributors', 'status': 'in_progress'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "71c4e613-48c8-4cf0-a928-0c7e6670d6b1", "tool_call_id": "call_tngiymm5i7ov5dubodstet59", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to analyze commits and issues to understand timeline and development history. Let me get commit history first." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1715-9460-7d11-92a7-cc2e1b3ca155", "tool_calls": [ { "name": "bash", "args": { "description": "Get commit history to understand development timeline", "command": "python /mnt/skills/public/github-deep-research/scripts/github_api.py bytedance deer-flow commits 10" }, "id": "call_negk0mcbvxu2m7qmv282eo79", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"sha\": \"3adb4e90cbf14e8dd0b34ab72fcd02e3b550635f\",\n \"node_id\": \"C_kwDOOlwd1doAKDNhZGI0ZTkwY2JmMTRlOGRkMGIzNGFiNzJmY2QwMmUzYjU1MDYzNWY\",\n \"commit\": {\n \"author\": {\n \"name\": \"Xun\",\n \"email\": \"liuxun@apache.org\",\n \"date\": \"2026-01-30T00:47:23Z\"\n },\n \"committer\": {\n \"name\": \"GitHub\",\n \"email\": \"noreply@github.com\",\n \"date\": \"2026-01-30T00:47:23Z\"\n },\n \"message\": \"fix: improve JSON repair handling for markdown code blocks (#841)\\n\\n* fix: improve JSON repair handling for markdown code blocks\\n\\n* unified import path\\n\\n* compress_crawl_udf\\n\\n* fix\\n\\n* reverse\",\n \"tree\": {\n \"sha\": \"ea837f8008d9b0a3f40ee850c2cbb0dbfa70e4a6\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/trees/ea837f8008d9b0a3f40ee850c2cbb0dbfa70e4a6\"\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/commits/3adb4e90cbf14e8dd0b34ab72fcd02e3b550635f\",\n \"comment_count\": 0,\n \"verification\": {\n \"verified\": true,\n \"reason\": \"valid\",\n \"signature\": \"-----BEGIN PGP SIGNATURE-----\\n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\\ng+E3Y9gYgD8nufxsrZzu\\n=4voY\\n-----END PGP SIGNATURE-----\\n\",\n \"payload\": \"tree ea837f8008d9b0a3f40ee850c2cbb0dbfa70e4a6\\nparent 756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\\nauthor Xun 1769734043 +0800\\ncommitter GitHub 1769734043 +0800\\n\\nfix: improve JSON repair handling for markdown code blocks (#841)\\n\\n* fix: improve JSON repair handling for markdown code blocks\\n\\n* unified import path\\n\\n* compress_crawl_udf\\n\\n* fix\\n\\n* reverse\",\n \"verified_at\": \"2026-01-30T00:47:24Z\"\n }\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/3adb4e90cbf14e8dd0b34ab72fcd02e3b550635f\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/3adb4e90cbf14e8dd0b34ab72fcd02e3b550635f\",\n \"comments_url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/3adb4e90cbf14e8dd0b34ab72fcd02e3b550635f/comments\",\n \"author\": {\n \"login\": \"xunliu\",\n \"id\": 3677382,\n \"node_id\": \"MDQ6VXNlcjM2NzczODI=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/3677382?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/xunliu\",\n \"html_url\": \"https://github.com/xunliu\",\n \"followers_url\": \"https://api.github.com/users/xunliu/followers\",\n \"following_url\": \"https://api.github.com/users/xunliu/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/xunliu/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/xunliu/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/xunliu/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/xunliu/orgs\",\n \"repos_url\": \"https://api.github.com/users/xunliu/repos\",\n \"events_url\": \"https://api.github.com/users/xunliu/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/xunliu/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"committer\": {\n \"login\": \"web-flow\",\n \"id\": 19864447,\n \"node_id\": \"MDQ6VXNlcjE5ODY0NDQ3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/19864447?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/web-flow\",\n \"html_url\": \"https://github.com/web-flow\",\n \"followers_url\": \"https://api.github.com/users/web-flow/followers\",\n \"following_url\": \"https://api.github.com/users/web-flow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/web-flow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/web-flow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/web-flow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/web-flow/orgs\",\n \"repos_url\": \"https://api.github.com/users/web-flow/repos\",\n \"events_url\": \"https://api.github.com/users/web-flow/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/web-flow/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"parents\": [\n {\n \"sha\": \"756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\"\n }\n ]\n },\n {\n \"sha\": \"756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\",\n \"node_id\": \"C_kwDOOlwd1doAKDc1NjQyMWMzYWMzMGZkOWI4ZTdjZTFiYWQzZjYzZDUxODFkZTNlMWU\",\n \"commit\": {\n \"author\": {\n \"name\": \"Willem Jiang\",\n \"email\": \"willem.jiang@gmail.com\",\n \"date\": \"2026-01-28T13:25:16Z\"\n },\n \"committer\": {\n \"name\": \"GitHub\",\n \"email\": \"noreply@github.com\",\n \"date\": \"2026-01-28T13:25:16Z\"\n },\n \"message\": \"fix(mcp-tool): using the async invocation for MCP tools (#840)\",\n \"tree\": {\n \"sha\": \"34df778892fc9d594ed30fb3bd04f529cc475765\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/trees/34df778892fc9d594ed30fb3bd04f529cc475765\"\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/commits/756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\",\n \"comment_count\": 0,\n \"verification\": {\n \"verified\": true,\n \"reason\": \"valid\",\n \"signature\": \"-----BEGIN PGP SIGNATURE-----\\n\\nwsFcBAABCAAQBQJpeg48CRC1aQ7uu5UhlAAAyJ4QAEwmtWJ1OcOSzFRwPmuIE5lH\\nfwY5Y3d3x0A3vL9bJDcp+fiv4sK2DVUTGf6WWuvsMpyYXO//3ZWql5PjMZg+gV5j\\np+fbmaoSSwlilEBYOGSX95z72HlQQxem8P3X/ssJdTNR+SHoG6uVgZ9q2LuaXx2Z\\ns5GxMycZgaZMdTAbzyXnzATPJGg7GKUdFz0hm8RIzDA8mmopmlEHBQjjLKdmBZRY\\n4n1Ohn+7DP0dElpnI0aDNmAmI6DDjpjo7yjqI0YkRFJj9+N4pdjcZRq9NxuxRc+/\\n1b7oeDb6+VHbgA5aRezs062/V7dlmEQT2NRow9bUjLI0tdnhnRHrJh/1pr13xJrp\\ngNmZPLqblpU4FAiYu6cNoSSTU7cy0Ci6soWfCqLGt3FbIRMW7wkTSQhe54gBXyMH\\nZ1MSznsRGtnS6t3c3jMGX2RzpoASh/6mNx9u5ZJA8YyfJQ+G1hXDo7r/s1bj/Ffx\\nKSqeGfopxaJ/Hq/IaFwbL4UNZHOGTjQt8cSOqR269XjmZ+YVJnkymJ+bj/OoX4Sh\\nNrDMn98od7bjb6URQ3T2tpiicXFADKUuEwRCVMJ7nBY1pyvdPxYOEjDoQ6JXVmqu\\nMYDVWeGwzAX59F4Hphtv0MVC0l2w1F8Dc4ypiWjbr6qVWjLMRAjK3ZHbIjhawWA0\\noIERH+r47qh0P35Et6G7\\n=TOS8\\n-----END PGP SIGNATURE-----\\n\",\n \"payload\": \"tree 34df778892fc9d594ed30fb3bd04f529cc475765\\nparent ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\\nauthor Willem Jiang 1769606716 +0800\\ncommitter GitHub 1769606716 +0800\\n\\nfix(mcp-tool): using the async invocation for MCP tools (#840)\\n\\n\",\n \"verified_at\": \"2026-01-28T13:25:17Z\"\n }\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e\",\n \"comments_url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/756421c3ac30fd9b8e7ce1bad3f63d5181de3e1e/comments\",\n \"author\": {\n \"login\": \"WillemJiang\",\n \"id\": 219644,\n \"node_id\": \"MDQ6VXNlcjIxOTY0NA==\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/219644?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/WillemJiang\",\n \"html_url\": \"https://github.com/WillemJiang\",\n \"followers_url\": \"https://api.github.com/users/WillemJiang/followers\",\n \"following_url\": \"https://api.github.com/users/WillemJiang/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/WillemJiang/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/WillemJiang/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/WillemJiang/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/WillemJiang/orgs\",\n \"repos_url\": \"https://api.github.com/users/WillemJiang/repos\",\n \"events_url\": \"https://api.github.com/users/WillemJiang/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/WillemJiang/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"committer\": {\n \"login\": \"web-flow\",\n \"id\": 19864447,\n \"node_id\": \"MDQ6VXNlcjE5ODY0NDQ3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/19864447?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/web-flow\",\n \"html_url\": \"https://github.com/web-flow\",\n \"followers_url\": \"https://api.github.com/users/web-flow/followers\",\n \"following_url\": \"https://api.github.com/users/web-flow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/web-flow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/web-flow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/web-flow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/web-flow/orgs\",\n \"repos_url\": \"https://api.github.com/users/web-flow/repos\",\n \"events_url\": \"https://api.github.com/users/web-flow/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/web-flow/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"parents\": [\n {\n \"sha\": \"ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\"\n }\n ]\n },\n {\n \"sha\": \"ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\",\n \"node_id\": \"C_kwDOOlwd1doAKGVlMDJiOWY2MzdhYTg1OTk0M2I5ZWY0NWJiMjVlMGIwZjFiZjBhMGI\",\n \"commit\": {\n \"author\": {\n \"name\": \"Xun\",\n \"email\": \"liuxun@apache.org\",\n \"date\": \"2026-01-26T13:10:18Z\"\n },\n \"committer\": {\n \"name\": \"GitHub\",\n \"email\": \"noreply@github.com\",\n \"date\": \"2026-01-26T13:10:18Z\"\n },\n \"message\": \"feat: Generate a fallback report upon recursion limit hit (#838)\\n\\n* finish handle_recursion_limit_fallback\\n\\n* fix\\n\\n* renmae test file\\n\\n* fix\\n\\n* doc\\n\\n---------\\n\\nCo-authored-by: lxl0413 \",\n \"tree\": {\n \"sha\": \"32f77c190f78c6b3c1a3328e79b8af1e64813c16\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/trees/32f77c190f78c6b3c1a3328e79b8af1e64813c16\"\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/commits/ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\",\n \"comment_count\": 0,\n \"verification\": {\n \"verified\": true,\n \"reason\": \"valid\",\n \"signature\": \"-----BEGIN PGP SIGNATURE-----\\n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\\nM8ZGRWPADVlA6r5x1Ypa\\n=J6UX\\n-----END PGP SIGNATURE-----\\n\",\n \"payload\": \"tree 32f77c190f78c6b3c1a3328e79b8af1e64813c16\\nparent 9a34e322524447ba2f46a38a0bfd1ad7578efe25\\nauthor Xun 1769433018 +0800\\ncommitter GitHub 1769433018 +0800\\n\\nfeat: Generate a fallback report upon recursion limit hit (#838)\\n\\n* finish handle_recursion_limit_fallback\\n\\n* fix\\n\\n* renmae test file\\n\\n* fix\\n\\n* doc\\n\\n---------\\n\\nCo-authored-by: lxl0413 \",\n \"verified_at\": \"2026-01-26T13:10:19Z\"\n }\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b\",\n \"comments_url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/ee02b9f637aa859943b9ef45bb25e0b0f1bf0a0b/comments\",\n \"author\": {\n \"login\": \"xunliu\",\n \"id\": 3677382,\n \"node_id\": \"MDQ6VXNlcjM2NzczODI=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/3677382?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/xunliu\",\n \"html_url\": \"https://github.com/xunliu\",\n \"followers_url\": \"https://api.github.com/users/xunliu/followers\",\n \"following_url\": \"https://api.github.com/users/xunliu/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/xunliu/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/xunliu/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/xunliu/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/xunliu/orgs\",\n \"repos_url\": \"https://api.github.com/users/xunliu/repos\",\n \"events_url\": \"https://api.github.com/users/xunliu/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/xunliu/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"committer\": {\n \"login\": \"web-flow\",\n \"id\": 19864447,\n \"node_id\": \"MDQ6VXNlcjE5ODY0NDQ3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/19864447?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/web-flow\",\n \"html_url\": \"https://github.com/web-flow\",\n \"followers_url\": \"https://api.github.com/users/web-flow/followers\",\n \"following_url\": \"https://api.github.com/users/web-flow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/web-flow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/web-flow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/web-flow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/web-flow/orgs\",\n \n[... Observation truncated due to length ...]\ndirect_response\\n\\nUse locale from state instead of tool_args to avoid potential side effects. The locale is already properly passed from frontend via state.\\n\\n* fix: only fallback to planner when clarification is enabled\\n\\nIn legacy mode (BRANCH 1), no tool calls should end the workflow gracefully instead of falling back to planner. This fixes the test_coordinator_node_no_tool_calls integration test.\\n\\n---------\\n\\nCo-authored-by: Willem Jiang \",\n \"verified_at\": \"2025-12-13T12:25:46Z\"\n }\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/c686ab70162a87de28f673357751d121a9b5f00e\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/c686ab70162a87de28f673357751d121a9b5f00e\",\n \"comments_url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/c686ab70162a87de28f673357751d121a9b5f00e/comments\",\n \"author\": {\n \"login\": \"blueberrycongee\",\n \"id\": 117764480,\n \"node_id\": \"U_kgDOBwTxgA\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/117764480?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/blueberrycongee\",\n \"html_url\": \"https://github.com/blueberrycongee\",\n \"followers_url\": \"https://api.github.com/users/blueberrycongee/followers\",\n \"following_url\": \"https://api.github.com/users/blueberrycongee/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/blueberrycongee/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/blueberrycongee/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/blueberrycongee/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/blueberrycongee/orgs\",\n \"repos_url\": \"https://api.github.com/users/blueberrycongee/repos\",\n \"events_url\": \"https://api.github.com/users/blueberrycongee/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/blueberrycongee/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"committer\": {\n \"login\": \"web-flow\",\n \"id\": 19864447,\n \"node_id\": \"MDQ6VXNlcjE5ODY0NDQ3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/19864447?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/web-flow\",\n \"html_url\": \"https://github.com/web-flow\",\n \"followers_url\": \"https://api.github.com/users/web-flow/followers\",\n \"following_url\": \"https://api.github.com/users/web-flow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/web-flow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/web-flow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/web-flow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/web-flow/orgs\",\n \"repos_url\": \"https://api.github.com/users/web-flow/repos\",\n \"events_url\": \"https://api.github.com/users/web-flow/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/web-flow/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"parents\": [\n {\n \"sha\": \"a6d8deee8b380d89d74a95058f82d7e218651fe5\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/a6d8deee8b380d89d74a95058f82d7e218651fe5\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/a6d8deee8b380d89d74a95058f82d7e218651fe5\"\n }\n ]\n },\n {\n \"sha\": \"a6d8deee8b380d89d74a95058f82d7e218651fe5\",\n \"node_id\": \"C_kwDOOlwd1doAKGE2ZDhkZWVlOGIzODBkODlkNzRhOTUwNThmODJkN2UyMTg2NTFmZTU\",\n \"commit\": {\n \"author\": {\n \"name\": \"dependabot[bot]\",\n \"email\": \"49699333+dependabot[bot]@users.noreply.github.com\",\n \"date\": \"2025-12-12T02:36:47Z\"\n },\n \"committer\": {\n \"name\": \"GitHub\",\n \"email\": \"noreply@github.com\",\n \"date\": \"2025-12-12T02:36:47Z\"\n },\n \"message\": \"build(deps): bump next from 15.4.8 to 15.4.10 in /web (#758)\\n\\nBumps [next](https://github.com/vercel/next.js) from 15.4.8 to 15.4.10.\\n- [Release notes](https://github.com/vercel/next.js/releases)\\n- [Changelog](https://github.com/vercel/next.js/blob/canary/release.js)\\n- [Commits](https://github.com/vercel/next.js/compare/v15.4.8...v15.4.10)\\n\\n---\\nupdated-dependencies:\\n- dependency-name: next\\n dependency-version: 15.4.10\\n dependency-type: direct:production\\n...\\n\\nSigned-off-by: dependabot[bot] \\nCo-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>\",\n \"tree\": {\n \"sha\": \"d9ea46f718b5b8c6db3bb19892af53959715c86a\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/trees/d9ea46f718b5b8c6db3bb19892af53959715c86a\"\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/commits/a6d8deee8b380d89d74a95058f82d7e218651fe5\",\n \"comment_count\": 0,\n \"verification\": {\n \"verified\": true,\n \"reason\": \"valid\",\n \"signature\": \"-----BEGIN PGP SIGNATURE-----\\n\\nwsFcBAABCAAQBQJpO3+/CRC1aQ7uu5UhlAAANKAQAKuLHAuZHMWIPDFP8+u7LuWo\\n0MyzDTgPIT5aD8Jx2qDVQlf4/Xx1U67iZTAE9K2HpPIGVPEyAkHO8ArIT2vdyVZH\\neWBPeDkE1YhunqeGMhBuo7aFPiBG1DpcLP9MdvwQ/FZjXb29Vyvn8hZHhJAnVs/O\\nf1UzyQ4Xa/AlecOiQ+OzAALQlaa+DNHCUqknXPOEtACzmxNeLBD+dD/lH0dj9Zt5\\nKB5HBtl5gYR0p82mXrLes/13zb18J+JF59f6JVbs479szXhI8d3VWYp/KY+v89ps\\nE23FBNa9XV5LMRNpgPx6W4gPz0BlJU+O/fCaF0xz2E/AYBR7btIQBajsoHf3dEyp\\n1sNO/1Qn9EMZTyysZFb0Beuv0EaUyMJhDuGShs5m3qPSGmAlqFUOq1JPDaPTcae1\\ngfWRBJ4uZkACF9bfUqCsGfwt6SWUIU3rB1JXo+aNn5dx94vmihIgjtvDI6YyHu8j\\nDAAK1oXzjHQU4uka84wgxr+XJWs1svu4KEU9ngMipuDtsHzBIo/LYZY3HSGAg/wI\\nko4XdoqrjDHScaNa7E0bv/qypV8ATWWcwItB2JxlpjDW8LISxB1ZZSsQ3DeiID95\\nKueBRZjv0QVusDLQckMIb+j7ajJ4oZoJeUNb8mxobOja5pR61jW8Zr/a3g+u3Ree\\nGx5eqOhnxOdpa5gVxde2\\n=ADXq\\n-----END PGP SIGNATURE-----\\n\",\n \"payload\": \"tree d9ea46f718b5b8c6db3bb19892af53959715c86a\\nparent 4c2592ac85d8af7c8eb8c47de6c7208a27254620\\nauthor dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> 1765507007 +0800\\ncommitter GitHub 1765507007 +0800\\n\\nbuild(deps): bump next from 15.4.8 to 15.4.10 in /web (#758)\\n\\nBumps [next](https://github.com/vercel/next.js) from 15.4.8 to 15.4.10.\\n- [Release notes](https://github.com/vercel/next.js/releases)\\n- [Changelog](https://github.com/vercel/next.js/blob/canary/release.js)\\n- [Commits](https://github.com/vercel/next.js/compare/v15.4.8...v15.4.10)\\n\\n---\\nupdated-dependencies:\\n- dependency-name: next\\n dependency-version: 15.4.10\\n dependency-type: direct:production\\n...\\n\\nSigned-off-by: dependabot[bot] \\nCo-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>\",\n \"verified_at\": \"2025-12-12T02:36:47Z\"\n }\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/a6d8deee8b380d89d74a95058f82d7e218651fe5\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/a6d8deee8b380d89d74a95058f82d7e218651fe5\",\n \"comments_url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/a6d8deee8b380d89d74a95058f82d7e218651fe5/comments\",\n \"author\": {\n \"login\": \"dependabot[bot]\",\n \"id\": 49699333,\n \"node_id\": \"MDM6Qm90NDk2OTkzMzM=\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/in/29110?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/dependabot%5Bbot%5D\",\n \"html_url\": \"https://github.com/apps/dependabot\",\n \"followers_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/followers\",\n \"following_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/orgs\",\n \"repos_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/repos\",\n \"events_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/dependabot%5Bbot%5D/received_events\",\n \"type\": \"Bot\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"committer\": {\n \"login\": \"web-flow\",\n \"id\": 19864447,\n \"node_id\": \"MDQ6VXNlcjE5ODY0NDQ3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/19864447?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/web-flow\",\n \"html_url\": \"https://github.com/web-flow\",\n \"followers_url\": \"https://api.github.com/users/web-flow/followers\",\n \"following_url\": \"https://api.github.com/users/web-flow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/web-flow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/web-flow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/web-flow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/web-flow/orgs\",\n \"repos_url\": \"https://api.github.com/users/web-flow/repos\",\n \"events_url\": \"https://api.github.com/users/web-flow/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/web-flow/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"parents\": [\n {\n \"sha\": \"4c2592ac85d8af7c8eb8c47de6c7208a27254620\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/4c2592ac85d8af7c8eb8c47de6c7208a27254620\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/4c2592ac85d8af7c8eb8c47de6c7208a27254620\"\n }\n ]\n },\n {\n \"sha\": \"4c2592ac85d8af7c8eb8c47de6c7208a27254620\",\n \"node_id\": \"C_kwDOOlwd1doAKDRjMjU5MmFjODVkOGFmN2M4ZWI4YzQ3ZGU2YzcyMDhhMjcyNTQ2MjA\",\n \"commit\": {\n \"author\": {\n \"name\": \"blueberrycongee\",\n \"email\": \"117764480+blueberrycongee@users.noreply.github.com\",\n \"date\": \"2025-12-11T13:21:37Z\"\n },\n \"committer\": {\n \"name\": \"GitHub\",\n \"email\": \"noreply@github.com\",\n \"date\": \"2025-12-11T13:21:37Z\"\n },\n \"message\": \"docs: add more MCP integration examples (#441) (#754)\",\n \"tree\": {\n \"sha\": \"4d67ceecd42b971d340aff6c1ae8f249ce31a35b\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/trees/4d67ceecd42b971d340aff6c1ae8f249ce31a35b\"\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/git/commits/4c2592ac85d8af7c8eb8c47de6c7208a27254620\",\n \"comment_count\": 0,\n \"verification\": {\n \"verified\": true,\n \"reason\": \"valid\",\n \"signature\": \"-----BEGIN PGP SIGNATURE-----\\n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\\n42iokDgSxur35QC7iTVU\\n=/Tal\\n-----END PGP SIGNATURE-----\\n\",\n \"payload\": \"tree 4d67ceecd42b971d340aff6c1ae8f249ce31a35b\\nparent ec99338c9a164c168b735a89a197fc189350783e\\nauthor blueberrycongee <117764480+blueberrycongee@users.noreply.github.com> 1765459297 +0800\\ncommitter GitHub 1765459297 +0800\\n\\ndocs: add more MCP integration examples (#441) (#754)\\n\\n\",\n \"verified_at\": \"2025-12-11T13:21:38Z\"\n }\n },\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/4c2592ac85d8af7c8eb8c47de6c7208a27254620\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/4c2592ac85d8af7c8eb8c47de6c7208a27254620\",\n \"comments_url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/4c2592ac85d8af7c8eb8c47de6c7208a27254620/comments\",\n \"author\": {\n \"login\": \"blueberrycongee\",\n \"id\": 117764480,\n \"node_id\": \"U_kgDOBwTxgA\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/117764480?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/blueberrycongee\",\n \"html_url\": \"https://github.com/blueberrycongee\",\n \"followers_url\": \"https://api.github.com/users/blueberrycongee/followers\",\n \"following_url\": \"https://api.github.com/users/blueberrycongee/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/blueberrycongee/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/blueberrycongee/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/blueberrycongee/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/blueberrycongee/orgs\",\n \"repos_url\": \"https://api.github.com/users/blueberrycongee/repos\",\n \"events_url\": \"https://api.github.com/users/blueberrycongee/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/blueberrycongee/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"committer\": {\n \"login\": \"web-flow\",\n \"id\": 19864447,\n \"node_id\": \"MDQ6VXNlcjE5ODY0NDQ3\",\n \"avatar_url\": \"https://avatars.githubusercontent.com/u/19864447?v=4\",\n \"gravatar_id\": \"\",\n \"url\": \"https://api.github.com/users/web-flow\",\n \"html_url\": \"https://github.com/web-flow\",\n \"followers_url\": \"https://api.github.com/users/web-flow/followers\",\n \"following_url\": \"https://api.github.com/users/web-flow/following{/other_user}\",\n \"gists_url\": \"https://api.github.com/users/web-flow/gists{/gist_id}\",\n \"starred_url\": \"https://api.github.com/users/web-flow/starred{/owner}{/repo}\",\n \"subscriptions_url\": \"https://api.github.com/users/web-flow/subscriptions\",\n \"organizations_url\": \"https://api.github.com/users/web-flow/orgs\",\n \"repos_url\": \"https://api.github.com/users/web-flow/repos\",\n \"events_url\": \"https://api.github.com/users/web-flow/events{/privacy}\",\n \"received_events_url\": \"https://api.github.com/users/web-flow/received_events\",\n \"type\": \"User\",\n \"user_view_type\": \"public\",\n \"site_admin\": false\n },\n \"parents\": [\n {\n \"sha\": \"ec99338c9a164c168b735a89a197fc189350783e\",\n \"url\": \"https://api.github.com/repos/bytedance/deer-flow/commits/ec99338c9a164c168b735a89a197fc189350783e\",\n \"html_url\": \"https://github.com/bytedance/deer-flow/commit/ec99338c9a164c168b735a89a197fc189350783e\"\n }\n ]\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "cf1dbdfb-4d22-40af-9519-02989ef036e3", "tool_call_id": "call_negk0mcbvxu2m7qmv282eo79", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to check issues and PRs to understand community activity and development timeline. Let me also search for more information about DeerFlow 2.0 and alternatives." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1715-c42c-7762-b3c1-13bb52afd2a3", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "completed" }, { "content": "Analyze community activity and contributors", "status": "completed" }, { "content": "Research timeline and development history", "status": "in_progress" }, { "content": "Compare with alternatives and assess market position", "status": "pending" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_qde6zcan07wkfzz3d3hm29o6", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'completed'}, {'content': 'Investigate technical architecture and features', 'status': 'completed'}, {'content': 'Analyze community activity and contributors', 'status': 'completed'}, {'content': 'Research timeline and development history', 'status': 'in_progress'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "0ed43144-dc82-418f-8a66-f39c825b0b40", "tool_call_id": "call_qde6zcan07wkfzz3d3hm29o6", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1715-fcd3-7570-b927-cddbd26f3250", "tool_calls": [ { "name": "web_search", "args": { "query": "DeerFlow alternatives deep research frameworks 2025 comparison" }, "id": "call_uz1r6yqbc0s9hlm5fleds6cj", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"title\": \"[Up-to-date] Awesome Agentic Deep Research Resources - GitHub\",\n \"url\": \"https://github.com/DavidZWZ/Awesome-Deep-Research\",\n \"snippet\": \"DeerFlow: ByteDance's research and analysis solution (May 9, 2025); Deep Research: Alibaba's Qwen-powered research assistant (May 14, 2025); Kimi\"\n },\n {\n \"title\": \"A Live Benchmark for User-Centric Deep Research in the Wild - arXiv\",\n \"url\": \"https://arxiv.org/html/2510.14240v1\",\n \"snippet\": \"We conduct a comprehensive evaluation of 17 state-of-the-art open-sourced and proprietary agentic systems, which can usually be grouped into three categories: (1) Single-agent systems with web search capabilities, including GPT-5 (OpenAI, 2025a) , GPT-4.1 (OpenAI, 2024), GPT-5-mini (OpenAI, 2025b), Gemini 2.5 Pro (DeepMind, 2025b), Gemini 2.5 Flash (DeepMind, 2025a), Claude 4 Sonnet (Anthropic, 2025a), Claude 4.1 Opus (Anthropic, 2025b), Perplexity Sonar Reasoning (Perplexity, 2025a), and Perplexity Sonar Reasoning Pro (Perplexity, 2025b); (2) Single-agent deep research systems, which feature extended reasoning depth and longer thinking time, including OpenAI o3 Deep Research (OpenAI, 2025c), OpenAI o4-mini Deep Research (OpenAI, 2025d), Perplexity Sonar Deep Research (AI, 2025b), Grok-4 Deep Research (Expert) (xAI, 2025b), and Gemini Deep Research (DeepMind, 2025c); (3) Multi-agent deep research systems, which coordinate a team of specialized agents to decompose complex queries. With these changes, Deerflow+ completed the full evaluation suite without token-limit failures and produced higher-quality reports: better retention of retrieved evidence, improved formatting and factual consistency, and more reliable performance on presentation checks tied to citation management, particularly P4 (Citation Completeness) and P9 (Format Consistency) in Figure 22 Deerflow (vanilla) ‣ Appendix C Deerflow+ ‣ LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild\\\").\"\n },\n {\n \"title\": \"Comparative Analysis of Deep Research Tools\",\n \"url\": \"https://trilogyai.substack.com/p/comparative-analysis-of-deep-research\",\n \"snippet\": \"Both tech giants and open-source communities have introduced solutions in late 2024 and early 2025 – notably all branding this feature as **“Deep Research.”** This analysis compares **proprietary solutions** (Google’s *Gemini Deep Research*, OpenAI’s *ChatGPT Deep Research*, *Perplexity AI Deep Research*, and xAI’s *Grok 3 DeepSearch*) against prominent **open-source projects** (e.g. OpenAI’s Deep Research is similar in concept: it is an **agentic mode in ChatGPT** that autonomously searches the web, analyzes data (including the ability to use tools like Python code if needed), and returns a detailed report. Most of the proprietary tools focus on textual analysis of web content, but OpenAI and some open-source ones extend to analyzing **local documents** provided by the user, enabling custom data to be included in the research. The development of deep research tools in this short span has **set new standards for AI-assisted research**: it’s no longer impressive for an AI to just answer questions – it should show its work, cite sources, handle multiple modalities, possibly use external tools, and integrate into workflows.\"\n },\n {\n \"title\": \"DeerFlow vs. OpenAI deep research Comparison - SourceForge\",\n \"url\": \"https://sourceforge.net/software/compare/DeerFlow-vs-OpenAI-deep-research/\",\n \"snippet\": \"Compare DeerFlow vs. OpenAI deep research using this comparison chart. Compare price, features, and reviews of the software side-by-side to make the best\"\n },\n {\n \"title\": \"Navigating the Landscape of Deep Research Frameworks - Oreate AI\",\n \"url\": \"https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks/c6ebff6d21ddce5a1c238b680171fe77\",\n \"snippet\": \"DeerFlow stands out with its complete web user interface (WEBUI) and integrated coder capabilities for article parsing and data analysis.\"\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_search", "id": "5037c63c-1cee-4181-acb5-641ffeca6cfa", "tool_call_id": "call_uz1r6yqbc0s9hlm5fleds6cj", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to check the report template to understand the structure I should follow. Let me read the template file." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1716-262f-7861-8b55-641ed6ebf9df", "tool_calls": [ { "name": "read_file", "args": { "description": "Read report template to understand structure", "path": "/mnt/skills/public/github-deep-research/assets/report_template.md" }, "id": "call_tao79nxthz2t4tz8mmgdt54n", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[!NOTE] Generate this report in user's own language.\n\n# {TITLE}\n\n- **Research Date:** {DATE}\n- **Timestamp:** {TIMESTAMP}\n- **Confidence Level:** {CONFIDENCE_LEVEL}\n- **Subject:** {SUBJECT_DESCRIPTION}\n\n---\n\n## Repository Information\n\n- **Name:** {REPOSITORY_NAME}\n- **Description:** {REPOSITORY_DESCRIPTION}\n- **URL:** {REPOSITORY_URL}\n- **Stars:** {REPOSITORY_STARS}\n- **Forks:** {REPOSITORY_FORKS}\n- **Open Issues:** {REPOSITORY_OPEN_ISSUES}\n- **Language(s):** {REPOSITORY_LANGUAGES}\n- **License:** {REPOSITORY_LICENSE}\n- **Created At:** {REPOSITORY_CREATED_AT}\n- **Updated At:** {REPOSITORY_UPDATED_AT}\n- **Pushed At:** {REPOSITORY_PUSHED_AT}\n- **Topics:** {REPOSITORY_TOPICS}\n\n---\n\n## Executive Summary\n\n{EXECUTIVE_SUMMARY}\n\n---\n\n## Complete Chronological Timeline\n\n### PHASE 1: {PHASE_1_NAME}\n\n#### {PHASE_1_PERIOD}\n\n{PHASE_1_CONTENT}\n\n### PHASE 2: {PHASE_2_NAME}\n\n#### {PHASE_2_PERIOD}\n\n{PHASE_2_CONTENT}\n\n### PHASE 3: {PHASE_3_NAME}\n\n#### {PHASE_3_PERIOD}\n\n{PHASE_3_CONTENT}\n\n---\n\n## Key Analysis\n\n### {ANALYSIS_SECTION_1_TITLE}\n\n{ANALYSIS_SECTION_1_CONTENT}\n\n### {ANALYSIS_SECTION_2_TITLE}\n\n{ANALYSIS_SECTION_2_CONTENT}\n\n---\n\n## Architecture / System Overview\n\n```mermaid\nflowchart TD\n A[Component A] --> B[Component B]\n B --> C[Component C]\n C --> D[Component D]\n```\n\n{ARCHITECTURE_DESCRIPTION}\n\n---\n\n## Metrics & Impact Analysis\n\n### Growth Trajectory\n\n```\n{METRICS_TIMELINE}\n```\n\n### Key Metrics\n\n| Metric | Value | Assessment |\n|--------|-------|------------|\n| {METRIC_1} | {VALUE_1} | {ASSESSMENT_1} |\n| {METRIC_2} | {VALUE_2} | {ASSESSMENT_2} |\n| {METRIC_3} | {VALUE_3} | {ASSESSMENT_3} |\n\n---\n\n## Comparative Analysis\n\n### Feature Comparison\n\n| Feature | {SUBJECT} | {COMPETITOR_1} | {COMPETITOR_2} |\n|---------|-----------|----------------|----------------|\n| {FEATURE_1} | {SUBJ_F1} | {COMP1_F1} | {COMP2_F1} |\n| {FEATURE_2} | {SUBJ_F2} | {COMP1_F2} | {COMP2_F2} |\n| {FEATURE_3} | {SUBJ_F3} | {COMP1_F3} | {COMP2_F3} |\n\n### Market Positioning\n\n{MARKET_POSITIONING}\n\n---\n\n## Strengths & Weaknesses\n\n### Strengths\n\n{STRENGTHS}\n\n### Areas for Improvement\n\n{WEAKNESSES}\n\n---\n\n## Key Success Factors\n\n{SUCCESS_FACTORS}\n\n---\n\n## Sources\n\n### Primary Sources\n\n{PRIMARY_SOURCES}\n\n### Media Coverage\n\n{MEDIA_SOURCES}\n\n### Academic / Technical Sources\n\n{ACADEMIC_SOURCES}\n\n### Community Sources\n\n{COMMUNITY_SOURCES}\n\n---\n\n## Confidence Assessment\n\n**High Confidence (90%+) Claims:**\n{HIGH_CONFIDENCE_CLAIMS}\n\n**Medium Confidence (70-89%) Claims:**\n{MEDIUM_CONFIDENCE_CLAIMS}\n\n**Lower Confidence (50-69%) Claims:**\n{LOW_CONFIDENCE_CLAIMS}\n\n---\n\n## Research Methodology\n\nThis report was compiled using:\n\n1. **Multi-source web search** - Broad discovery and targeted queries\n2. **GitHub repository analysis** - Commits, issues, PRs, activity metrics\n3. **Content extraction** - Official docs, technical articles, media coverage\n4. **Cross-referencing** - Verification across independent sources\n5. **Chronological reconstruction** - Timeline from timestamped data\n6. **Confidence scoring** - Claims weighted by source reliability\n\n**Research Depth:** {RESEARCH_DEPTH}\n**Time Scope:** {TIME_SCOPE}\n**Geographic Scope:** {GEOGRAPHIC_SCOPE}\n\n---\n\n**Report Prepared By:** Github Deep Research by DeerFlow\n**Date:** {REPORT_DATE}\n**Report Version:** 1.0\n**Status:** Complete\n", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "read_file", "id": "c761be0a-b98a-4b5c-80a7-3c7cd05202ff", "tool_call_id": "call_tao79nxthz2t4tz8mmgdt54n", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to gather more specific information about DeerFlow's technical architecture, features, and market position. Let me search for more detailed technical information." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1716-4c8a-7c53-8268-2ceb1d32a865", "tool_calls": [ { "name": "web_search", "args": { "query": "\"DeerFlow\" architecture LangGraph multi-agent framework" }, "id": "call_vkvb6py13eqcerfu89xoumr9", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "[\n {\n \"title\": \"DeerFlow\",\n \"url\": \"https://deerflow.tech/\",\n \"snippet\": \"Multi-Agent Architecture. Experience the agent teamwork with our Supervisor + ... Build with confidence using the LangChain and LangGraph frameworks.\"\n },\n {\n \"title\": \"Create Your Own Deep Research Agent with DeerFlow\",\n \"url\": \"https://thesequence.substack.com/p/the-sequence-engineering-661-create\",\n \"snippet\": \"At the heart of DeerFlow lies a modular agent orchestration architecture powered by LangGraph and LangChain. This structure enables\"\n },\n {\n \"title\": \"DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep ...\",\n \"url\": \"https://www.linkedin.com/pulse/deerflow-modular-multi-agent-framework-deep-research-ramichetty-pbhxc\",\n \"snippet\": \"# DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep Research Automation. Released under the MIT license, DeerFlow empowers developers and researchers to automate complex workflows, from academic research to enterprise-grade data analysis. DeerFlow overcomes this limitation through a multi-agent architecture, where each agent specializes in a distinct function, such as task planning, knowledge retrieval, code execution, or report generation. This architecture ensures that DeerFlow can handle diverse research scenarios, such as synthesizing literature reviews, generating data visualizations, or drafting multimodal content. These integrations make DeerFlow a powerful tool for research analysts, data scientists, and technical writers seeking to combine reasoning, execution, and content creation in a single platform. DeerFlow represents a significant advancement in research automation, combining the power of multi-agent coordination, LLM-driven reasoning, and human-in-the-loop collaboration. Its modular architecture, deep tool integrations, and developer-friendly design make it a compelling choice for researchers and organizations seeking to accelerate complex workflows.\"\n },\n {\n \"title\": \"ByteDance DeerFlow: Multi AI Agent framework for Deep Research\",\n \"url\": \"https://medium.com/data-science-in-your-pocket/bytedance-deerflow-multi-ai-agent-framework-for-deep-research-acfbc4d90fbd\",\n \"snippet\": \"A community-driven multi-agent research framework. It combines language models, search engines, web crawlers, and text-to-speech features to automate deep\"\n },\n {\n \"title\": \"Build multi-agent systems with LangGraph and Amazon Bedrock\",\n \"url\": \"https://aws.amazon.com/blogs/machine-learning/build-multi-agent-systems-with-langgraph-and-amazon-bedrock/\",\n \"snippet\": \"The framework provides fine-grained control over both the flow and state of your agent applications. LangGraph models agent workflows as graphs.\"\n }\n]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "web_search", "id": "73b7513e-b259-4044-911f-9816db2b2d62", "tool_call_id": "call_vkvb6py13eqcerfu89xoumr9", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1716-808d-7ef1-b54c-8b51011bf7b6", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "completed" }, { "content": "Analyze community activity and contributors", "status": "completed" }, { "content": "Research timeline and development history", "status": "completed" }, { "content": "Compare with alternatives and assess market position", "status": "in_progress" }, { "content": "Compile comprehensive research report", "status": "pending" } ] }, "id": "call_xew5okokzq2q7oa0z1yg0exk", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'completed'}, {'content': 'Investigate technical architecture and features', 'status': 'completed'}, {'content': 'Analyze community activity and contributors', 'status': 'completed'}, {'content': 'Research timeline and development history', 'status': 'completed'}, {'content': 'Compare with alternatives and assess market position', 'status': 'in_progress'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "8956e012-ea79-4adb-b68e-dc09207c17a6", "tool_call_id": "call_xew5okokzq2q7oa0z1yg0exk", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "现在我需要编译一份全面的研究报告。让我先整理一下所有收集到的信息，然后创建报告。" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1716-b3d5-7973-b528-2957b8b5f44a", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "completed" }, { "content": "Analyze community activity and contributors", "status": "completed" }, { "content": "Research timeline and development history", "status": "completed" }, { "content": "Compare with alternatives and assess market position", "status": "completed" }, { "content": "Compile comprehensive research report", "status": "in_progress" } ] }, "id": "call_ex42b2ptrqexrw0m45ikwuqo", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'completed'}, {'content': 'Investigate technical architecture and features', 'status': 'completed'}, {'content': 'Analyze community activity and contributors', 'status': 'completed'}, {'content': 'Research timeline and development history', 'status': 'completed'}, {'content': 'Compare with alternatives and assess market position', 'status': 'completed'}, {'content': 'Compile comprehensive research report', 'status': 'in_progress'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "2f55ceee-6d9f-498c-b288-6d9eeb9a4a16", "tool_call_id": "call_ex42b2ptrqexrw0m45ikwuqo", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I'll compile the comprehensive research report based on all the information gathered. Let me create the final report." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1716-ee75-73b1-a93e-e6553d9a8f0a", "tool_calls": [ { "name": "write_file", "args": { "description": "Create comprehensive research report on DeerFlow", "path": "/mnt/user-data/workspace/research_deerflow_20260201.md", "content": "# DeerFlow Deep Research Report\n\n- **Research Date:** 2026-02-01\n- **Timestamp:** 2026-02-01, Sunday\n- **Confidence Level:** High (90%+)\n- **Subject:** ByteDance's Open-Source Multi-Agent Deep Research Framework\n\n---\n\n## Repository Information\n\n- **Name:** bytedance/deer-flow\n- **Description:** DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community [DeerFlow GitHub Repository](https://github.com/bytedance/deer-flow)\n- **URL:** https://github.com/bytedance/deer-flow\n- **Stars:** 19,531\n- **Forks:** 2,452\n- **Open Issues:** 196\n- **Language(s):** Python (1,292,574 bytes), TypeScript (503,143 bytes), CSS (15,128 bytes), JavaScript (7,906 bytes), Dockerfile (2,197 bytes), Makefile (1,352 bytes), Shell (1,152 bytes), Batchfile (497 bytes)\n- **License:** MIT\n- **Created At:** 2025-05-07T02:50:19Z\n- **Updated At:** 2026-02-01T01:07:38Z\n- **Pushed At:** 2026-01-30T00:47:23Z\n- **Topics:** agent, agentic, agentic-framework, agentic-workflow, ai, ai-agents, bytedance, deep-research, langchain, langgraph, langmanus, llm, multi-agent, nodejs, podcast, python, typescript\n\n---\n\n## Executive Summary\n\nDeerFlow (Deep Exploration and Efficient Research Flow) is an open-source multi-agent research automation framework developed by ByteDance and released under the MIT license in May 2025 [Create Your Own Deep Research Agent with DeerFlow](https://thesequence.substack.com/p/the-sequence-engineering-661-create). The framework implements a graph-based orchestration of specialized agents that automate research pipelines end-to-end, combining language models with tools like web search engines, crawlers, and Python execution. With 19,531 stars and 2,452 forks on GitHub, DeerFlow has established itself as a significant player in the deep research automation space, offering both console and web UI options with support for local LLM deployment and extensive tool integrations [DeerFlow: A Game-Changer for Automated Research and Content Creation](https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a).\n\n---\n\n## Complete Chronological Timeline\n\n### PHASE 1: Project Inception and Initial Development\n\n#### May 2025 - July 2025\n\nDeerFlow was created by ByteDance and open-sourced on May 7, 2025, with the initial commit establishing the core multi-agent architecture built on LangGraph and LangChain frameworks [DeerFlow GitHub Repository](https://github.com/bytedance/deer-flow). The project quickly gained traction in the AI community due to its comprehensive approach to research automation, combining web search, crawling, and code execution capabilities. Early development focused on establishing the modular agent system with specialized roles including Coordinator, Planner, Researcher, Coder, and Reporter components.\n\n### PHASE 2: Feature Expansion and Community Growth\n\n#### August 2025 - December 2025\n\nDuring this period, DeerFlow underwent significant feature expansion including MCP (Model Context Protocol) integration, text-to-speech capabilities, podcast generation, and support for multiple search engines (Tavily, InfoQuest, Brave Search, DuckDuckGo, Arxiv) [DeerFlow: Multi-Agent AI For Research Automation 2025](https://firexcore.com/blog/what-is-deerflow/). The framework gained attention for its human-in-the-loop collaboration features, allowing users to review and edit research plans before execution. Community contributions grew substantially, with 88 contributors participating in the project by early 2026, and the framework was integrated into the FaaS Application Center of Volcengine for cloud deployment.\n\n### PHASE 3: Maturity and DeerFlow 2.0 Transition\n\n#### January 2026 - Present\n\nAs of February 2026, DeerFlow has entered a transition phase to DeerFlow 2.0, with active development continuing on the main branch [DeerFlow Official Website](https://deerflow.tech/). Recent commits show ongoing improvements to JSON repair handling, MCP tool integration, and fallback report generation mechanisms. The framework now supports private knowledgebases including RAGFlow, Qdrant, Milvus, and VikingDB, along with Docker and Docker Compose deployment options for production environments.\n\n---\n\n## Key Analysis\n\n### Technical Architecture and Design Philosophy\n\nDeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis [DeerFlow: A Game-Changer for Automated Research and Content Creation](https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a). The system is built on LangGraph, enabling a flexible state-based workflow where components communicate through a well-defined message passing system. The architecture employs a streamlined workflow with specialized agents:\n\n```mermaid\nflowchart TD\n A[Coordinator] --> B[Planner]\n B --> C{Enough Context?}\n C -->|No| D[Research Team]\n D --> E[Researcher
Web Search & Crawling]\n D --> F[Coder
Python Execution]\n E --> C\n F --> C\n C -->|Yes| G[Reporter]\n G --> H[Final Report]\n```\n\nThe Coordinator serves as the entry point managing workflow lifecycle, initiating research processes based on user input and delegating tasks to the Planner when appropriate. The Planner analyzes research objectives and creates structured execution plans, determining if sufficient context is available or if more research is needed. The Research Team consists of specialized agents including a Researcher for web searches and information gathering, and a Coder for handling technical tasks using Python REPL tools. Finally, the Reporter aggregates findings and generates comprehensive research reports [Create Your Own Deep Research Agent with DeerFlow](https://thesequence.substack.com/p/the-sequence-engineering-661-create).\n\n### Core Features and Capabilities\n\nDeerFlow offers extensive capabilities for deep research automation:\n\n1. **Multi-Engine Search Integration**: Supports Tavily (default), InfoQuest (BytePlus's AI-optimized search), Brave Search, DuckDuckGo, and Arxiv for scientific papers [DeerFlow: Multi-Agent AI For Research Automation 2025](https://firexcore.com/blog/what-is-deerflow/).\n\n2. **Advanced Crawling Tools**: Includes Jina (default) and InfoQuest crawlers with configurable parameters, timeout settings, and powerful content extraction capabilities.\n\n3. **MCP (Model Context Protocol) Integration**: Enables seamless integration with diverse research tools and methodologies for private domain access, knowledge graphs, and web browsing.\n\n4. **Private Knowledgebase Support**: Integrates with RAGFlow, Qdrant, Milvus, VikingDB, MOI, and Dify for research on users' private documents.\n\n5. **Human-in-the-Loop Collaboration**: Features intelligent clarification mechanisms, plan review and editing capabilities, and auto-acceptance options for streamlined workflows.\n\n6. **Content Creation Tools**: Includes podcast generation with text-to-speech synthesis, PowerPoint presentation creation, and Notion-style block editing for report refinement.\n\n7. **Multi-Language Support**: Provides README documentation in English, Simplified Chinese, Japanese, German, Spanish, Russian, and Portuguese.\n\n### Development and Community Ecosystem\n\nThe project demonstrates strong community engagement with 88 contributors and 19,531 GitHub stars as of February 2026 [DeerFlow GitHub Repository](https://github.com/bytedance/deer-flow). Key contributors include Henry Li (203 contributions), Willem Jiang (130 contributions), and Daniel Walnut (25 contributions), representing a mix of ByteDance employees and open-source community members. The framework maintains comprehensive documentation including configuration guides, API documentation, FAQ sections, and multiple example research reports covering topics from quantum computing to AI adoption in healthcare.\n\n---\n\n## Metrics & Impact Analysis\n\n### Growth Trajectory\n\n```\nTimeline: May 2025 - February 2026\nStars: 0 → 19,531 (exponential growth)\nForks: 0 → 2,452 (strong community adoption)\nContributors: 0 → 88 (active development ecosystem)\nOpen Issues: 196 (ongoing maintenance and feature development)\n```\n\n### Key Metrics\n\n| Metric | Value | Assessment |\n|--------|-------|------------|\n| GitHub Stars | 19,531 | Exceptional popularity for research framework |\n| Forks | 2,452 | Strong community adoption and potential derivatives |\n| Contributors | 88 | Healthy open-source development ecosystem |\n| Open Issues | 196 | Active maintenance and feature development |\n| Primary Language | Python (1.29MB) | Main development language with extensive libraries |\n| Secondary Language | TypeScript (503KB) | Modern web UI implementation |\n| Repository Age | ~9 months | Rapid development and feature expansion |\n| License | MIT | Permissive open-source licensing |\n\n---\n\n## Comparative Analysis\n\n### Feature Comparison\n\n| Feature | DeerFlow | OpenAI Deep Research | LangChain OpenDeepResearch |\n|---------|-----------|----------------------|----------------------------|\n| Multi-Agent Architecture | ✅ | ❌ | ✅ |\n| Local LLM Support | ✅ | ❌ | ✅ |\n| MCP Integration | ✅ | ❌ | ❌ |\n| Web Search Engines | Multiple (5+) | Limited | Limited |\n| Code Execution | ✅ Python REPL | Limited | ✅ |\n| Podcast Generation | ✅ | ❌ | ❌ |\n| Presentation Creation | ✅ | ❌ | ❌ |\n| Private Knowledgebase | ✅ (6+ options) | Limited | Limited |\n| Human-in-the-Loop | ✅ | Limited | ✅ |\n| Open Source | ✅ MIT | ❌ | ✅ Apache 2.0 |\n\n### Market Positioning\n\nDeerFlow occupies a unique position in the deep research framework landscape by combining enterprise-grade multi-agent orchestration with extensive tool integrations and open-source accessibility [Navigating the Landscape of Deep Research Frameworks](https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks-a-comprehensive-comparison/0dc13e48eb8c756650112842c8d1a184]. While proprietary solutions like OpenAI's Deep Research offer polished user experiences, DeerFlow provides greater flexibility through local deployment options, custom tool integration, and community-driven development. The framework particularly excels in scenarios requiring specialized research workflows, integration with private data sources, or deployment in regulated environments where cloud-based solutions may not be feasible.\n\n---\n\n## Strengths & Weaknesses\n\n### Strengths\n\n1. **Comprehensive Multi-Agent Architecture**: DeerFlow's sophisticated agent orchestration enables complex research workflows beyond single-agent systems [Create Your Own Deep Research Agent with DeerFlow](https://thesequence.substack.com/p/the-sequence-engineering-661-create).\n\n2. **Extensive Tool Integration**: Support for multiple search engines, crawling tools, MCP services, and private knowledgebases provides unmatched flexibility.\n\n3. **Local Deployment Capabilities**: Unlike many proprietary solutions, DeerFlow supports local LLM deployment, offering privacy, cost control, and customization options.\n\n4. **Human Collaboration Features**: Intelligent clarification mechanisms and plan editing capabilities bridge the gap between automated research and human oversight.\n\n5. **Active Community Development**: With 88 contributors and regular updates, the project benefits from diverse perspectives and rapid feature evolution.\n\n6. **Production-Ready Deployment**: Docker support, cloud integration (Volcengine), and comprehensive documentation facilitate enterprise adoption.\n\n### Areas for Improvement\n\n1. **Learning Curve**: The extensive feature set and configuration options may present challenges for new users compared to simpler single-purpose tools.\n\n2. **Resource Requirements**: Local deployment with multiple agents and tools may demand significant computational resources.\n\n3. **Documentation Complexity**: While comprehensive, the documentation spans multiple languages and may benefit from more streamlined onboarding guides.\n\n4. **Integration Complexity**: Advanced features like MCP integration and custom tool development require technical expertise beyond basic usage.\n\n5. **Version Transition**: The ongoing move to DeerFlow 2.0 may create temporary instability or compatibility concerns for existing deployments.\n\n---\n\n## Key Success Factors\n\n1. **ByteDance Backing**: Corporate sponsorship provides resources, expertise, and credibility while maintaining open-source accessibility [DeerFlow: A Game-Changer for Automated Research and Content Creation](https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a).\n\n2. **Modern Technical Foundation**: Built on LangGraph and LangChain, DeerFlow leverages established frameworks while adding significant value through multi-agent orchestration.\n\n3. **Community-Driven Development**: Active contributor community ensures diverse use cases, rapid bug fixes, and feature evolution aligned with real-world needs.\n\n4. **Comprehensive Feature Set**: Unlike narrowly focused tools, DeerFlow addresses the complete research workflow from information gathering to content creation.\n\n5. **Production Deployment Options**: Cloud integration, Docker support, and enterprise features facilitate adoption beyond experimental use cases.\n\n6. **Multi-Language Accessibility**: Documentation and interface support for multiple languages expands global reach and adoption potential.\n\n---\n\n## Sources\n\n### Primary Sources\n\n1. **DeerFlow GitHub Repository**: Official source code, documentation, and development history [DeerFlow GitHub Repository](https://github.com/bytedance/deer-flow)\n2. **DeerFlow Official Website**: Platform showcasing features, case studies, and deployment options [DeerFlow Official Website](https://deerflow.tech/)\n3. **GitHub API Data**: Repository metrics, contributor statistics, and commit history\n\n### Media Coverage\n\n1. **The Sequence Engineering**: Technical analysis of DeerFlow architecture and capabilities [Create Your Own Deep Research Agent with DeerFlow](https://thesequence.substack.com/p/the-sequence-engineering-661-create)\n2. **Medium Articles**: Community perspectives on DeerFlow implementation and use cases [DeerFlow: A Game-Changer for Automated Research and Content Creation](https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a)\n3. **YouTube Demonstrations**: Video walkthroughs of DeerFlow functionality and local deployment [ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)](https://www.youtube.com/watch?v=Ui0ovCVDYGs)\n\n### Technical Sources\n\n1. **FireXCore Analysis**: Feature overview and technical assessment [DeerFlow: Multi-Agent AI For Research Automation 2025](https://firexcore.com/blog/what-is-deerflow/)\n2. **Oreate AI Comparison**: Framework benchmarking and market positioning analysis [Navigating the Landscape of Deep Research Frameworks](https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks-a-comprehensive-comparison/0dc13e48eb8c756650112842c8d1a184)\n\n---\n\n## Confidence Assessment\n\n**High Confidence (90%+) Claims:**\n- DeerFlow was created by ByteDance and open-sourced under MIT license in May 2025\n- The framework implements multi-agent architecture using LangGraph and LangChain\n- Current GitHub metrics: 19,531 stars, 2,452 forks, 88 contributors, 196 open issues\n- Supports multiple search engines including Tavily, InfoQuest, Brave Search\n- Includes features for podcast generation, presentation creation, and human collaboration\n\n**Medium Confidence (70-89%) Claims:**\n- Specific performance benchmarks compared to proprietary alternatives\n- Detailed breakdown of enterprise adoption rates and use cases\n- Exact resource requirements for various deployment scenarios\n\n**Lower Confidence (50-69%) Claims:**\n- Future development roadmap beyond DeerFlow 2.0 transition\n- Specific enterprise customer implementations and case studies\n- Detailed comparison with emerging competitors not yet widely documented\n\n---\n\n## Research Methodology\n\nThis report was compiled using:\n\n1. **Multi-source web search** - Broad discovery and targeted queries across technical publications, media coverage, and community discussions\n2. **GitHub repository analysis** - Direct API queries for commits, issues, PRs, contributor activity, and repository metrics\n3. **Content extraction** - Official documentation, technical articles, video demonstrations, and community resources\n4. **Cross-referencing** - Verification across independent sources including technical analysis, media coverage, and community feedback\n5. **Chronological reconstruction** - Timeline development from timestamped commit history and release documentation\n6. **Confidence scoring** - Claims weighted by source reliability, corroboration across multiple sources, and recency of information\n\n**Research Depth:** Comprehensive technical and market analysis\n**Time Scope:** May 2025 - February 2026 (9-month development period)\n**Geographic Scope:** Global open-source community with ByteDance corporate backing\n\n---\n\n**Report Prepared By:** Github Deep Research by DeerFlow\n**Date:** 2026-02-01\n**Report Version:** 1.0\n**Status:** Complete" }, "id": "call_l2m5ymrn2iwc1k3wnnirveue", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "OK", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_file", "id": "a6d352e9-ae98-4c3c-9d9a-5bccbff4d732", "tool_call_id": "call_l2m5ymrn2iwc1k3wnnirveue", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "Now I need to copy the report to the outputs directory and present it to the user. Let me first check if the outputs directory exists, then copy the file there." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1719-00ad-7bc1-b30e-3fa09bed1a45", "tool_calls": [ { "name": "bash", "args": { "description": "Copy research report to outputs directory", "command": "cp /mnt/user-data/workspace/research_deerflow_20260201.md /mnt/user-data/outputs/research_deerflow_20260201.md" }, "id": "call_h2kkzwzc97ie6e5drv2dmgkc", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "(no output)", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "de496c30-a92a-4a6d-b20b-73588000c1b4", "tool_call_id": "call_h2kkzwzc97ie6e5drv2dmgkc", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1719-29c7-77f0-bb45-364560e460f7", "tool_calls": [ { "name": "write_todos", "args": { "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "completed" }, { "content": "Analyze community activity and contributors", "status": "completed" }, { "content": "Research timeline and development history", "status": "completed" }, { "content": "Compare with alternatives and assess market position", "status": "completed" }, { "content": "Compile comprehensive research report", "status": "completed" } ] }, "id": "call_loo956iz39o7t182dshw8qn5", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'completed'}, {'content': 'Investigate technical architecture and features', 'status': 'completed'}, {'content': 'Analyze community activity and contributors', 'status': 'completed'}, {'content': 'Research timeline and development history', 'status': 'completed'}, {'content': 'Compare with alternatives and assess market position', 'status': 'completed'}, {'content': 'Compile comprehensive research report', 'status': 'completed'}]", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_todos", "id": "cd16b5da-c1f6-44aa-ae7f-9256b78d0a43", "tool_call_id": "call_loo956iz39o7t182dshw8qn5", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "" }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1719-634a-74c0-9cce-87f0aba1ee7b", "tool_calls": [ { "name": "present_files", "args": { "filepaths": [ "/mnt/user-data/outputs/research_deerflow_20260201.md" ] }, "id": "call_onca19ev52bbsvkybzsxwyp9", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Successfully presented files", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "present_files", "id": "9cb681ef-8859-4a7c-8411-984aa229eebf", "tool_call_id": "call_onca19ev52bbsvkybzsxwyp9", "artifact": null, "status": "success" }, { "content": "The complete research report has been saved to `/mnt/user-data/outputs/research_deerflow_20260201.md` and is now available for your review. The report includes detailed analysis of the technical architecture, development timeline, community metrics, comparative analysis with alternatives, and confidence assessments for all claims.", "response_metadata": { "finish_reason": "stop", "model_name": "deepseek-v3-2-251201", "service_tier": "default", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c1719-8bc3-7101-9d80-c368e1e14271", "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null }, { "content": [ { "type": "text", "text": "Great job! Then make a cool webpage according to your report." } ], "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": "6f621f69-d5b7-40c4-b812-3de65e029821" }, { "content": "", "additional_kwargs": { "reasoning_content": "The user wants me to create a cool webpage based on the DeerFlow research report I just generated. This is a perfect use case for the frontend-design skill. Let me load that skill first to understand the workflow and best practices." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "kimi-k2.5", "system_fingerprint": "fpv0_e3b2d471", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c171a-c54f-7243-912f-09c9ee5ef763", "tool_calls": [ { "name": "read_file", "args": { "description": "Load frontend-design skill for creating the webpage", "path": "/mnt/skills/public/frontend-design/SKILL.md" }, "id": "read_file:31", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.\nlicense: Complete terms in LICENSE.txt\n---\n\nThis skill guides creation of distinctive, production-grade frontend interfaces that avoid generic \"AI slop\" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.\n\nThe user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.\n\n## Output Requirements\n\n**MANDATORY**: The entry HTML file MUST be named `index.html`. This is a strict requirement for all generated frontend projects to ensure compatibility with standard web hosting and deployment workflows.\n\n## Design Thinking\n\nBefore coding, understand the context and commit to a BOLD aesthetic direction:\n- **Purpose**: What problem does this interface solve? Who uses it?\n- **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.\n- **Constraints**: Technical requirements (framework, performance, accessibility).\n- **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember?\n\n**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.\n\nThen implement working code (HTML/CSS/JS, React, Vue, etc.) that is:\n- Production-grade and functional\n- Visually striking and memorable\n- Cohesive with a clear aesthetic point-of-view\n- Meticulously refined in every detail\n\n## Frontend Aesthetics Guidelines\n\nFocus on:\n- **Typography**: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font.\n- **Color & Theme**: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes.\n- **Motion**: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise.\n- **Spatial Composition**: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density.\n- **Backgrounds & Visual Details**: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays.\n\nNEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.\n\nInterpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.\n\n**IMPORTANT**: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well.\n\n## Branding Requirement\n\n**MANDATORY**: Every generated frontend interface MUST include a \"Created By Deerflow\" signature. This branding element should be:\n- **Subtle and unobtrusive** - it should NEVER compete with or distract from the main content and functionality\n- **Clickable**: The signature MUST be a clickable link that opens https://deerflow.tech in a new tab (target=\"_blank\")\n- Integrated naturally into the design, feeling like an intentional design element rather than an afterthought\n- Small in size, using muted colors or reduced opacity that blend harmoniously with the overall aesthetic\n\n**IMPORTANT**: The branding should be discoverable but not prominent. Users should notice the main interface first; the signature is a quiet attribution, not a focal point.\n\n**Creative Implementation Ideas** (choose one that best matches your design aesthetic):\n\n1. **Floating Corner Badge**: A small, elegant badge fixed to a corner with subtle hover effects (e.g., gentle glow, slight scale-up, color shift)\n\n2. **Artistic Watermark**: A semi-transparent diagonal text or logo pattern in the background, barely visible but adds texture\n\n3. **Integrated Border Element**: Part of a decorative border or frame around the content - the signature becomes an organic part of the design structure\n\n4. **Animated Signature**: A small signature that elegantly writes itself on page load, or reveals on scroll near the bottom\n\n5. **Contextual Integration**: Blend into the theme - for a retro design, use a vintage stamp look; for minimalist, a single small icon or monogram \"DF\" with tooltip\n\n6. **Cursor Trail or Easter Egg**: A very subtle approach where the branding appears as a micro-interaction (e.g., holding cursor still reveals a tiny signature, or appears in a creative loading state)\n\n7. **Decorative Divider**: Incorporate into a decorative line, separator, or ornamental element on the page\n\n8. **Glassmorphism Card**: A tiny floating glass-effect card in a corner with blur backdrop\n\nExample code patterns:\n```html\n\n✦ Deerflow\n\n\nDF\n\n\n\n```\n\n**Design Principle**: The branding should feel like it belongs - a natural extension of your creative vision, not a mandatory stamp. Match the signature's style (typography, color, animation) to the overall aesthetic direction.\n\nRemember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision.\n", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "read_file", "id": "f75ca681-b1e7-425a-b34b-835c4fac153b", "tool_call_id": "read_file:31", "artifact": null, "status": "success" }, { "content": "I'll create a stunning, distinctive webpage based on the DeerFlow research report. Let me design something bold and memorable that captures the essence of this multi-agent research framework.", "additional_kwargs": { "reasoning_content": "Now I have the guidelines for creating the webpage. I need to create a cool, distinctive webpage based on the DeerFlow research report. Let me think about the design direction:\n\n1. **Purpose**: Showcase the DeerFlow research report in an engaging, interactive way\n2. **Tone**: Tech-forward, modern, research-focused, with a hint of futuristic/agentic theme (since DeerFlow is about multi-agent AI)\n3. **Differentiation**: I should create something that feels like a premium research presentation - maybe with:\n - A dark theme with accent colors\n - Interactive elements for the timeline\n - Animated metrics counters\n - A sophisticated multi-agent visual representation\n - Smooth scroll-triggered animations\n\nLet me create a bold, distinctive design. I'll go with:\n- **Theme**: Dark, sophisticated tech aesthetic with electric blue/teal accents\n- **Typography**: Distinctive fonts - maybe something like \"Space Grotesk\" for headers (actually, the skill says to avoid common choices like Space Grotesk), so let me pick something more unique. Maybe \"DM Serif Display\" for headlines and \"JetBrains Mono\" for code/metrics.\n- **Visual Style**: Multi-layered with subtle gradients, glassmorphism effects, and dynamic data visualizations\n- **Animations**: Scroll-triggered reveals, staggered content entry, animated numbers for metrics\n\nLet me create this as a single HTML file with embedded CSS and JavaScript." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "kimi-k2.5", "system_fingerprint": "fpv0_30fe32e5", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c171a-f728-7d12-ace4-5da5bdc01524", "tool_calls": [ { "name": "write_file", "args": { "description": "Create cool DeerFlow research report webpage", "path": "/mnt/user-data/outputs/index.html", "content": "\n\n\n \n \n DeerFlow Research Report 2026\n \n \n \n \n\n\n

\n\n \n\n

Research Report 2026

DeerFlow:
Multi-Agent Deep Research

A comprehensive analysis of ByteDance's open-source framework that combines language models with specialized tools for automated research workflows.

GitHub Stars

Forks

Contributors

MIT

License

\n\n

01 / Overview

Executive Summary

The framework that redefines automated research through intelligent multi-agent orchestration.

\n DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source multi-agent research automation framework developed by ByteDance and released under the MIT license in May 2025. The framework implements a graph-based orchestration of specialized agents that automate research pipelines end-to-end, combining language models with tools like web search engines, crawlers, and Python execution.\n

\n With 19,531 stars and 2,452 forks on GitHub, DeerFlow has established itself as a significant player in the deep research automation space, offering both console and web UI options with support for local LLM deployment and extensive tool integrations.\n

\n\n

02 / History

Development Timeline

From initial release to the upcoming DeerFlow 2.0 transition.

Phase 01

May — July 2025

Project Inception

DeerFlow was created by ByteDance and open-sourced on May 7, 2025. The initial release established the core multi-agent architecture built on LangGraph and LangChain frameworks, featuring specialized agents: Coordinator, Planner, Researcher, Coder, and Reporter.

Phase 02

August — December 2025

Feature Expansion

Major feature additions including MCP integration, text-to-speech capabilities, podcast generation, and support for multiple search engines (Tavily, InfoQuest, Brave Search, DuckDuckGo, Arxiv). The framework gained recognition for its human-in-the-loop collaboration features and was integrated into Volcengine's FaaS Application Center.

Phase 03

January 2026 — Present

DeerFlow 2.0 Transition

The project is transitioning to DeerFlow 2.0 with ongoing improvements to JSON repair handling, MCP tool integration, and fallback report generation. Now supports private knowledgebases including RAGFlow, Qdrant, Milvus, and VikingDB, along with comprehensive Docker deployment options.

\n\n

03 / System Design

Multi-Agent Architecture

A modular system built on LangGraph enabling flexible state-based workflows.

Coordinator

Entry point & workflow lifecycle

Planner

Task decomposition & planning

🔍 Researcher

Web search & crawling

💻 Coder

Python execution & analysis

Reporter

Report generation & synthesis

\n\n

04 / Capabilities

Key Features

Comprehensive tooling for end-to-end research automation.

🔍

Multi-Engine Search

Supports Tavily, InfoQuest (BytePlus), Brave Search, DuckDuckGo, and Arxiv for scientific papers with configurable parameters.

🔗

MCP Integration

Seamless integration with Model Context Protocol services for private domain access, knowledge graphs, and web browsing.

📚

Private Knowledgebase

Integrates with RAGFlow, Qdrant, Milvus, VikingDB, MOI, and Dify for research on users' private documents.

🤝

Human-in-the-Loop

Intelligent clarification mechanisms, plan review and editing, and auto-acceptance options for streamlined workflows.

🎙️

Content Creation

Podcast generation with TTS synthesis, PowerPoint creation, and Notion-style block editing for report refinement.

🐳

Production Ready

Docker and Docker Compose support, cloud deployment via Volcengine, and comprehensive API documentation.

\n\n

05 / Analysis

Competitive Comparison

How DeerFlow compares to other deep research solutions.

\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n

Feature	DeerFlow	OpenAI Deep Research	LangChain OpenDeepResearch
Multi-Agent Architecture	✓	✗	✓
Local LLM Support	✓	✗	✓
MCP Integration	✓	✗	✗
Code Execution	✓ Python REPL	Limited	✓
Podcast Generation	✓	✗	✗
Presentation Creation	✓	✗	✗
Private Knowledgebase	✓ (6+ options)	Limited	Limited
Open Source	✓ MIT	✗ Proprietary	✓ Apache 2.0

\n\n

06 / Assessment

Strengths & Considerations

Balanced evaluation of the framework's capabilities.

💪 Strengths

Comprehensive multi-agent architecture with specialized roles
Extensive tool integration across search, crawling, and databases
Local LLM deployment support for privacy and cost control
Human collaboration features bridging automation and oversight
Active community with 88+ contributors
Production-ready with Docker and cloud deployment options

⚠️ Considerations

Extensive feature set may present learning curve for new users
Local deployment with multiple agents demands significant resources
Advanced features require technical expertise beyond basic usage
Version 2.0 transition may create temporary compatibility concerns
Integration complexity for custom MCP tools and workflows

\n\n

07 / Conclusion

Final Assessment

High confidence evaluation based on comprehensive analysis.

\n DeerFlow represents a significant advancement in research automation, combining the power of multi-agent coordination, LLM-driven reasoning, and human-in-the-loop collaboration. Its modular architecture, deep tool integrations, and developer-friendly design make it a compelling choice for researchers and organizations seeking to accelerate complex workflows.\n

\n With ByteDance backing, an active open-source community, and continuous feature development, DeerFlow is well-positioned to remain a leading framework in the deep research automation space. The upcoming DeerFlow 2.0 transition promises further enhancements to an already robust platform.\n

\n\n \n\n Created By Deerflow\n\n \n\n" }, "id": "write_file:32", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "OK", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "write_file", "id": "6b1d411a-840a-4654-85df-0b7e1207d23d", "tool_call_id": "write_file:32", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "The webpage is created. Let me verify it exists and then present it to the user." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "kimi-k2.5", "system_fingerprint": "fpv0_30fe32e5", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c171d-95f5-7bf2-9801-926c2b84b235", "tool_calls": [ { "name": "bash", "args": { "description": "Verify the webpage file exists", "command": "ls -la /mnt/user-data/outputs/index.html" }, "id": "bash:33", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "-rw-r--r-- 1 gem gem 39626 Feb 1 10:52 /mnt/user-data/outputs/index.html", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "bash", "id": "b5cb24be-1c32-4a59-8909-2f3439b31d9e", "tool_call_id": "bash:33", "artifact": null, "status": "success" }, { "content": "", "additional_kwargs": { "reasoning_content": "The file is created successfully. Let me present it to the user." }, "response_metadata": { "finish_reason": "tool_calls", "model_name": "kimi-k2.5", "system_fingerprint": "fpv0_30fe32e5", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c171d-ae2c-7731-a3db-bdd055d5fc35", "tool_calls": [ { "name": "present_files", "args": { "filepaths": ["/mnt/user-data/outputs/index.html"] }, "id": "present_files:34", "type": "tool_call" } ], "invalid_tool_calls": [], "usage_metadata": null }, { "content": "Successfully presented files", "additional_kwargs": {}, "response_metadata": {}, "type": "tool", "name": "present_files", "id": "2e59ab5b-4e6d-4c2e-a8dc-f39b9e3e3c58", "tool_call_id": "present_files:34", "artifact": null, "status": "success" }, { "content": "I've created a **stylish, production-grade webpage** based on the DeerFlow research report. Here's what makes it stand out:\n\n## Design Highlights\n\n**Visual Aesthetic**\n- **Dark tech theme** with electric teal/cyan accents that evoke an agentic, futuristic feel\n- **Dynamic background** with floating glow effects and a subtle grid pattern\n- **Sophisticated typography** using Playfair Display for headlines (elegant, editorial feel) and JetBrains Mono for technical elements\n\n**Interactive Features**\n- **Animated counters** that count up when scrolling into view (19,531 stars, 2,452 forks, 88 contributors)\n- **Scroll-triggered fade-in animations** for smooth content reveals\n- **Hover effects** on cards, navigation links, and architecture nodes\n- **Smooth scroll navigation** between sections\n\n**Content Sections**\n1. **Hero** - Dramatic intro with live metrics\n2. **Executive Summary** - Key insights in a glassmorphic card\n3. **Development Timeline** - Visual timeline with phases\n4. **Multi-Agent Architecture** - Interactive flow diagram showing Coordinator → Planner → Research Team → Reporter\n5. **Feature Grid** - 6 key capabilities with icons\n6. **Competitive Comparison** - Side-by-side feature table\n7. **Strengths & Considerations** - Balanced SWOT analysis\n8. **Conclusion** - Final assessment\n\n**Responsive Design**\n- Fully responsive layout that adapts from desktop to mobile\n- Flexible grid systems and overflow handling for tables\n- Touch-friendly navigation and interactions\n\nThe page includes the \"Created By Deerflow\" badge in the bottom-right corner that links to [deerflow.tech](https://deerflow.tech). You can view the rendered page by opening the file!", "additional_kwargs": { "reasoning_content": "The webpage has been created and presented. Let me provide a summary of what was built." }, "response_metadata": { "finish_reason": "stop", "model_name": "kimi-k2.5", "system_fingerprint": "fpv0_e3b2d471", "model_provider": "deepseek" }, "type": "ai", "name": null, "id": "lc_run--019c171d-ba55-7d80-8ca2-2cd76980e733", "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null } ], "thread_data": { "workspace_path": "/Users/henry/Desktop/deer-flow/backend/.deer-flow/threads/fe3f7974-1bcb-4a01-a950-79673baafefd/user-data/workspace", "uploads_path": "/Users/henry/Desktop/deer-flow/backend/.deer-flow/threads/fe3f7974-1bcb-4a01-a950-79673baafefd/user-data/uploads", "outputs_path": "/Users/henry/Desktop/deer-flow/backend/.deer-flow/threads/fe3f7974-1bcb-4a01-a950-79673baafefd/user-data/outputs" }, "title": "Deer-Flow Research and Analysis", "artifacts": [ "/mnt/user-data/outputs/index.html", "/mnt/user-data/outputs/research_deerflow_20260201.md" ], "todos": [ { "content": "Extract repository metadata using GitHub API", "status": "completed" }, { "content": "Fetch README and repository information", "status": "completed" }, { "content": "Analyze repository structure and languages", "status": "completed" }, { "content": "Research DeerFlow project overview and purpose", "status": "completed" }, { "content": "Investigate technical architecture and features", "status": "completed" }, { "content": "Analyze community activity and contributors", "status": "completed" }, { "content": "Research timeline and development history", "status": "completed" }, { "content": "Compare with alternatives and assess market position", "status": "completed" }, { "content": "Compile comprehensive research report", "status": "completed" } ], "viewed_images": {} }, "next": [], "tasks": [], "metadata": { "model_name": "kimi-k2.5", "mode": "pro", "thinking_enabled": true, "is_plan_mode": true, "graph_id": "lead_agent", "assistant_id": "bee7d354-5df5-5f26-a978-10ea053f620d", "user_id": "", "created_by": "system", "thread_id": "fe3f7974-1bcb-4a01-a950-79673baafefd", "checkpoint_id": "1f0ff188-2c9f-62b6-8063-2b82a90f68f5", "checkpoint_ns": "", "run_id": "019c171a-c1ce-79c3-9e18-0974f81e19a1", "run_attempt": 1, "langgraph_version": "1.0.6", "langgraph_api_version": "0.6.38", "langgraph_plan": "developer", "langgraph_host": "self-hosted", "langgraph_api_url": "http://127.0.0.1:2024", "source": "loop", "step": 119, "parents": {}, "langgraph_auth_user_id": "", "langgraph_request_id": "eb930093-4e3b-4237-b141-a793111bc025" }, "created_at": "2026-02-01T02:52:39.444222+00:00", "checkpoint": { "checkpoint_id": "1f0ff191-247b-6e28-8077-c6ae37cb0bc6", "thread_id": "fe3f7974-1bcb-4a01-a950-79673baafefd", "checkpoint_ns": "" }, "parent_checkpoint": { "checkpoint_id": "1f0ff191-2479-6baa-8076-feaaf42a66ed", "thread_id": "fe3f7974-1bcb-4a01-a950-79673baafefd", "checkpoint_ns": "" }, "interrupts": [], "checkpoint_id": "1f0ff191-247b-6e28-8077-c6ae37cb0bc6", "parent_checkpoint_id": "1f0ff191-2479-6baa-8076-feaaf42a66ed" }

DeerFlow:Multi-Agent Deep Research

Executive Summary

Development Timeline

Project Inception

Feature Expansion

DeerFlow 2.0 Transition

Multi-Agent Architecture

Key Features

Multi-Engine Search

MCP Integration

Private Knowledgebase

Human-in-the-Loop

Content Creation

Production Ready

Competitive Comparison

Strengths & Considerations

💪 Strengths

⚠️ Considerations

Final Assessment

DeerFlow:
Multi-Agent Deep Research