{"name":"Open Deep Research: A Configurable Open-Source Deep Research Agent","description":"Open Deep Research is a fully open-source, configurable agent designed for deep research applications. It supports various model providers, search tools, and Model Context Protocol (MCP) servers, offering performance comparable to other popular deep research agents. Developed by LangChain, it leverages LangGraph for robust agent orchestration and provides extensive customization options.","github":"https://github.com/langchain-ai/open_deep_research","url":"https://osrepos.com/repo/langchain-ai-open_deep_research","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/langchain-ai-open_deep_research","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/langchain-ai-open_deep_research.md","json":"https://osrepos.com/repo/langchain-ai-open_deep_research.json","topics":["Python","AI Agents","Deep Research","LangChain","LangGraph","LLM","Open Source","Artificial Intelligence"],"keywords":["Python","AI Agents","Deep Research","LangChain","LangGraph","LLM","Open Source","Artificial Intelligence"],"stars":null,"summary":"Open Deep Research is a fully open-source, configurable agent designed for deep research applications. It supports various model providers, search tools, and Model Context Protocol (MCP) servers, offering performance comparable to other popular deep research agents. Developed by LangChain, it leverages LangGraph for robust agent orchestration and provides extensive customization options.","content":"## Introduction\n\nOpen Deep Research is a powerful, open-source deep research agent developed by LangChain. It is built to perform comprehensive research across a multitude of model providers, search tools, and MCP servers. This project stands out for its configurability and its performance, which is on par with many leading deep research agents, as demonstrated on the [Deep Research Bench leaderboard](https://huggingface.co/spaces/Ayanami0730/DeepResearch-Leaderboard \"Deep Research Bench Leaderboard\" target=\"_blank\"). The agent is designed to be simple to use while offering deep customization, making it a versatile tool for automated research tasks.\n\n## Installation\n\nTo get started with Open Deep Research, follow these steps:\n\n1.  **Clone the repository and activate a virtual environment:**\n\n    bash\n    git clone https://github.com/langchain-ai/open_deep_research.git\n    cd open_deep_research\n    uv venv\n    source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate\n    \n\n2.  **Install dependencies:**\n\n    bash\n    uv sync\n    # or\n    uv pip install -r pyproject.toml\n    \n\n3.  **Set up your `.env` file:**\n\n    bash\n    cp .env.example .env\n    \n\n4.  **Launch the agent with the LangGraph server locally:**\n\n    bash\n    uvx --refresh --from \"langgraph-cli[inmem]\" --with-editable . --python 3.11 langgraph dev --allow-blocking\n    \n\n    This command will open the LangGraph Studio UI in your browser, providing access to the agent's interface.\n\n## Examples\n\nOnce the LangGraph server is running, you can interact with the agent through the LangGraph Studio UI. Simply ask a question in the `messages` input field and click `Submit`. The agent's behavior can be extensively customized through its configurations, accessible via the \"Manage Assistants\" tab in the Studio UI.\n\nKey configuration areas include:\n\n*   **LLM Selection**: Open Deep Research supports a wide range of LLM providers. Different models can be assigned for specific tasks such as summarization, research, compression, and final report generation. For example, `openai:gpt-4.1-mini` might be used for summarization, while `openai:gpt-4.1` handles research and report writing. Models must support structured outputs and tool calling.\n*   **Search API**: By default, the agent uses the [Tavily](https://www.tavily.com/ \"Tavily Search API\" target=\"_blank\") search API, but it is compatible with various search tools and offers full MCP compatibility for native web search with Anthropic and OpenAI.\n*   **Other Settings**: The `configuration.py` file contains numerous other settings to fine-tune the agent's behavior, all accessible through the LangGraph Studio UI.\n\n## Why Use It\n\nOpen Deep Research offers several compelling reasons for its adoption:\n\n*   **High Performance**: It achieves competitive results on the Deep Research Bench leaderboard, ensuring high-quality research output.\n*   **Extensive Configurability**: Users can easily swap out LLM providers, search tools, and other parameters to tailor the agent to specific research needs and available resources.\n*   **Fully Open Source**: The project's open-source nature allows for transparency, community contributions, and deep customization beyond the default configurations.\n*   **Flexible Deployment**: Beyond local LangGraph Studio, it can be deployed to the [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/#deployment-options \"LangGraph Platform\" target=\"_blank\") or integrated into the [Open Agent Platform (OAP)](https://oap.langchain.com \"Open Agent Platform Demo\" target=\"_blank\"), enabling non-technical users to configure and utilize the agent.\n*   **Educational Resources**: LangChain provides a [free course on building open deep research with LangGraph](https://academy.langchain.com/courses/deep-research-with-langgraph \"Deep Research with LangGraph Course\" target=\"_blank\"), making it easier for developers to understand and extend the agent.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/langchain-ai/open_deep_research](https://github.com/langchain-ai/open_deep_research \"Open Deep Research GitHub\" target=\"_blank\")\n*   **Deep Research Bench Leaderboard**: [https://huggingface.co/spaces/Ayanami0730/DeepResearch-Leaderboard](https://huggingface.co/spaces/Ayanami0730/DeepResearch-Leaderboard \"Deep Research Bench Leaderboard\" target=\"_blank\")\n*   **Free Course: Deep Research with LangGraph**: [https://academy.langchain.com/courses/deep-research-with-langgraph](https://academy.langchain.com/courses/deep-research-with-langgraph \"Deep Research with LangGraph Course\" target=\"_blank\")\n*   **Blog Post: Evolution of Open Deep Research**: [https://rlancemartin.github.io/2025/07/30/bitter_lesson/](https://rlancemartin.github.io/2025/07/30/bitter_lesson/ \"Evolution Blog Post\" target=\"_blank\")\n*   **Blog Post: Open Deep Research Overview**: [https://blog.langchain.com/open-deep-research/](https://blog.langchain.com/open-deep-research/ \"Overview Blog Post\" target=\"_blank\")\n*   **Video Overview**: [https://www.youtube.com/watch?v=agGiWUpxkhg](https://www.youtube.com/watch?v=agGiWUpxkhg \"Video Overview\" target=\"_blank\")\n*   **Open Agent Platform (OAP) Demo**: [https://oap.langchain.com](https://oap.langchain.com \"Open Agent Platform Demo\" target=\"_blank\")","metrics":{"detailViews":9,"githubClicks":11},"dates":{"published":null,"modified":"2026-05-15T19:39:14.000Z"}}