Repository files navigation

Deep research has broken out as one of the most popular agent applications. This is a simple, configurable, fully open source deep research agent that works across many model providers, search tools, and MCP servers.

• Read more in ourblog
• See ourvideo for a quick overview

1. Clone the repository and activate a virtual environment:

git clone https://github.com/langchain-ai/open_deep_research.gitcd open_deep_researchuv venvsource .venv/bin/activate# On Windows: .venv\Scripts\activate

2. Install dependencies:

uv pip install -r pyproject.toml

3. Set up your.env file to customize the environment variables (for model selection, search tools, and other configuration settings):

cp .env.example .env

4. Launch the assistant with the LangGraph server locally to open LangGraph Studio in your browser:

# Install dependencies and start the LangGraph serveruvx --refresh --from"langgraph-cli[inmem]" --with-editable. --python 3.11 langgraph dev --allow-blocking

Use this to open the Studio UI:

- 🚀 API: http://127.0.0.1:2024- 🎨 Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024- 📚 API Docs: http://127.0.0.1:2024/docs

Ask a question in themessages input field and clickSubmit.

Open Deep Research offers extensive configuration options to customize the research process and model behavior. All configurations can be set via the web UI, environment variables, or by modifying the configuration directly.

• Max Structured Output Retries (default: 3): Maximum number of retries for structured output calls from models when parsing fails
• Allow Clarification (default: true): Whether to allow the researcher to ask clarifying questions before starting research
• Max Concurrent Research Units (default: 5): Maximum number of research units to run concurrently using sub-agents. Higher values enable faster research but may hit rate limits

• Search API (default: Tavily): Choose from Tavily (works with all models), OpenAI Native Web Search, Anthropic Native Web Search, or None
• Max Researcher Iterations (default: 3): Number of times the Research Supervisor will reflect on research and ask follow-up questions
• Max React Tool Calls (default: 5): Maximum number of tool calling iterations in a single researcher step

Open Deep Research uses multiple specialized models for different research tasks:

• Summarization Model (default:openai:gpt-4.1-nano): Summarizes research results from search APIs
• Research Model (default:openai:gpt-4.1): Conducts research and analysis
• Compression Model (default:openai:gpt-4.1-mini): Compresses research findings from sub-agents
• Final Report Model (default:openai:gpt-4.1): Writes the final comprehensive report

All models are configured usinginit_chat_model() API which supports providers like OpenAI, Anthropic, Google Vertex AI, and others.

Important Model Requirements:

1. Structured Outputs: All models must support structured outputs. Check supporthere.

2. Search API Compatibility: Research and Compression models must support your selected search API:

   • Anthropic search requires Anthropic models with web search capability
   • OpenAI search requires OpenAI models with web search capability
   • Tavily works with all models

3. Tool Calling: All models must support tool calling functionality

4. Special Configurations:

   • For OpenRouter: Followthis guide
   • For local models via Ollama: Seesetup instructions

Open Deep Research supports MCP servers to extend research capabilities.

Filesystem MCP Server provides secure file system operations with robust access control:

• Read, write, and manage files and directories
• Perform operations like reading file contents, creating directories, moving files, and searching
• Restrict operations to predefined directories for security
• Support for both command-line configuration and dynamic MCP roots

Example usage:

mcp-server-filesystem /path/to/allowed/dir1 /path/to/allowed/dir2

Remote MCP servers enable distributed agent coordination and support streamable HTTP requests. Unlike local servers, they can be multi-tenant and require more complex authentication.

Arcade MCP Server Example:

{"url":"https://api.arcade.dev/v1/mcps/ms_0ujssxh0cECutqzMgbtXSGnjorm","tools": ["Search_SearchHotels","Search_SearchOneWayFlights","Search_SearchRoundtripFlights"]}

Remote servers can be configured as authenticated or unauthenticated and support JWT-based authentication through OAuth endpoints.

A comprehensive batch evaluation system designed for detailed analysis and comparative studies.

• Multi-dimensional Scoring: Specialized evaluators with 0-1 scale ratings
• Dataset-driven Evaluation: Batch processing across multiple test cases

# Run comprehensive evaluation on LangSmith datasetspython tests/run_evaluate.py

• tests/run_evaluate.py: Main evaluation script
• tests/evaluators.py: Specialized evaluator functions
• tests/prompts.py: Evaluation prompts for each dimension

Follow thequickstart to start LangGraph server locally and test the agent out on LangGraph Studio.

You can easily deploy toLangGraph Platform.

Open Agent Platform (OAP) is a UI from which non-technical users can build and configure their own agents. OAP is great for allowing users to configure the Deep Researcher with different MCP tools and search APIs that are best suited to their needs and the problems that they want to solve.

We've deployed Open Deep Research to our public demo instance of OAP. All you need to do is add your API Keys, and you can test out the Deep Researcher for yourself! Try it outhere

You can also deploy your own instance of OAP, and make your own custom agents (like Deep Researcher) available on it to your users.

1. Deploy Open Agent Platform
2. Add Deep Researcher to OAP

Thesrc/legacy/ folder contains two earlier implementations that provide alternative approaches to automated research:

• Plan-and-Execute: Structured workflow with human-in-the-loop planning
• Sequential Processing: Creates sections one by one with reflection
• Interactive Control: Allows feedback and approval of report plans
• Quality Focused: Emphasizes accuracy through iterative refinement

• Supervisor-Researcher Architecture: Coordinated multi-agent system
• Parallel Processing: Multiple researchers work simultaneously
• Speed Optimized: Faster report generation through concurrency
• MCP Support: Extensive Model Context Protocol integration

Seesrc/legacy/legacy.md for detailed documentation, configuration options, and usage examples for both legacy implementations.