company-research-agent

Active
GitHub Python Apache-2.0

Description

An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on the backend for inference.

Key Features

  • Multi-agent pipeline with specialized nodes: CompanyAnalyzer, IndustryAnalyzer, FinancialAnalyst, NewsScanner
  • Dual model architecture using Gemini 2.5 Flash for synthesis and GPT-5.1 for report formatting
  • Tavily-powered content curation with AI relevance scoring and document deduplication
  • Async research processing with polling-based job tracking and real-time report streaming
  • Modern React frontend with progress visualization, PDF export, and Google Maps integration
  • Modular node-based architecture enabling easy addition of new research sources

Use Cases

💡 Generate comprehensive due diligence reports for potential business partners or acquisitions
💡 Research competitors with automated multi-source data gathering and synthesis
💡 Produce investor-ready company briefings with financial metrics and market analysis
💡 Automate market research workflows for venture capital and private equity teams
💡 Create structured company profiles combining news, financials, and industry positioning

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (2.2k stars)
  • Permissive open-source license (Apache-2.0)
  • Responsive to issues, low backlog

Quick Start

Clone the repo and run `./setup.sh` which auto-detects uv and installs dependencies. Set Tavily, Gemini, OpenAI, and Google Maps API keys in `.env`. Run `cd ui && npm install` for the frontend. Start with the setup script or manually run backend and frontend servers.

Related Projects