deep-research-agent

deepakj111/deep-research-agent
★ 0 stars Python 🤖 AI/LLM Updated today
Production-grade AI research agent: LangGraph + MCP servers + parallel web/arXiv/GitHub search → synthesized report with citations.
View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "deep-research-agent": {
      "command": "uvx",
      "args": [
        "deep-research-agent"
      ]
    }
  }
}

Or install with pip: pip install deep-research-agent

README Excerpt

An autonomous deep research agent that accepts a natural-language query and produces a **structured, cited, multi-source research report** — drawing from **live web search**, **academic papers (arXiv)**, and **GitHub repositories** simultaneously. Built with **LangGraph** for stateful agent orchestration, **Model Context Protocol (MCP)** for standardised tool integration, and a **multi-model synthesis** pipeline (GPT-4o + Claude Sonnet) with automated contradiction detection.

Tools (6)

ANTHROPIC_API_KEYGITHUB_TOKENLANGCHAIN_API_KEYMCP_JWT_SECRETOPENAI_API_KEYTAVILY_API_KEY