Open Deep Research: Build Your Own AI Researcher

Unveiling Open Deep Research: Your Customizable AI Research Assistant

In the rapidly evolving landscape of artificial intelligence, the ability to conduct deep, insightful research is paramount. Enter Open Deep Research, a groundbreaking open-source project that empowers developers and researchers to build and customize their own powerful AI research agents. Built with the flexibility of LangGraph, this project offers a fully configurable framework that seamlessly integrates with various model providers, search tools, and Model Context Protocol (MCP) servers.

What is Open Deep Research?

At its core, Open Deep Research provides a robust and adaptable agent designed for comprehensive data exploration and analysis. It excels at tasks ranging from summarizing complex information to generating detailed final reports. The project is characterized by its configurability, allowing users to fine-tune every aspect of the research process, from the AI models used for summarization and analysis to the search APIs and concurrency settings.

Key Features and Capabilities:

• Versatile Model Integration: Supports a wide array of model providers, including OpenAI, Anthropic, and Google Vertex AI, enabling users to select the best models for specific tasks like summarization, research, compression, and final report generation.
• Flexible Search Tools: Integrates with multiple search APIs such as Tavily, OpenAI Native Web Search, and Anthropic Native Web Search, ensuring broad data access.
• MCP Server Support: Extends research capabilities through Model Context Protocol (MCP) servers, allowing for advanced operations like file system management (local MCP servers) and distributed agent coordination (remote MCP servers).
• Customizable Configurations: Offers extensive settings that can be adjusted via a web UI, environment variables, or direct code modification, catering to diverse user preferences and project requirements.
• LangGraph Studio Integration: Provides a smooth deployment experience through LangGraph Studio, allowing for local server setup and interactive testing of the agent's capabilities.
• Open Agent Platform (OAP) Compatibility: Easily deployable on OAP, a user-friendly interface for non-technical users to build and configure agents, making the advanced capabilities of Open Deep Research accessible to a broader audience.
• Comprehensive Evaluation: Includes a batch evaluation system with multi-dimensional scoring and dataset-driven analysis for rigorous testing and improvement.
• Legacy Implementations: Offers alternative approaches in the src/legacy/ folder, including Workflow and Multi-Agent implementations, providing insights into different agent architectures.

Getting Started with Open Deep Research:

The project features a straightforward quickstart guide, making it accessible even for those new to complex AI agent development.

1. Clone the Repository:

   git clone https://github.com/langchain-ai/open_deep_research.git
   cd open_deep_research
   

2. Set Up Virtual Environment and Dependencies:

   uv venv
   source .venv/bin/activate # (or .venv\Scripts\activate on Windows)
   uv pip install -r pyproject.toml
   

3. Configure Environment Variables: Copy the example environment file and customize it:

   cp .env.example .env
   

4. Launch LangGraph Server:

   uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.11 langgraph dev --allow-blocking
   

This setup allows you to access the agent via API at http://127.0.0.1:2024 and interact with it through the LangGraph Studio UI at https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024.

Contributing and Exploration:

With over 6.7k stars and 891 forks on GitHub, Open Deep Research is a testament to its utility and the active community surrounding it. Developers are encouraged to explore the codebase, contribute to its development, and leverage its powerful features to build innovative AI-driven research solutions. Whether you're a seasoned AI practitioner or a curious developer, Open Deep Research offers a valuable platform to push the boundaries of automated research.