company-research-agent

An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages OpenRoute

What is company-research-agent?

An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages OpenRouter on the backend for rapid inference with any leading model.

Overview of company-research-agent

What it is

Company Research Agent is an open-source tool that turns a company name into a structured, source-backed briefing. It uses a FastAPI backend with a multi-agent research graph and a React frontend. The backend coordinates specialized research and synthesis steps; the interface tracks the job and lets you export the finished report as a PDF.

Key features

  • Researches a company’s business, industry, financial context, and recent news.
  • Uses Tavily search and relevance scoring to find and curate source material.
  • Synthesizes category briefings with Gemini and produces the final report with OpenAI models.
  • Streams research progress to the browser and supports PDF export.
  • Optionally persists jobs and reports in MongoDB.

Use cases

  • Conducting deep diligence on a company before a business meeting or investment.
  • Generating structured, source-backed briefings for competitive analysis.
  • Automating the collection and synthesis of company information from multiple sources.

Getting started

  1. Create a virtual environment and install the backend dependencies:bashuv venv .venvuv pip install -r requirements.txtIf you do not use uv, create the environment with python -m venv .venv and install with pip install -r requirements.txt.2. Create .env from the example and set the required backend keys:bashcp .env.example .env``````envGEMINI_API_KEY=your_gemini_keyOPENAI_API_KEY=your_openai_key# Optional fallback when no per-session Tavily key is suppliedTAVILY_API_KEY=your_tavily_key# MONGODB_URI=optional_mongodb_connection_string3. Configure the frontend:bashcp ui/.env.development.example ui/.env.development.localcd ui && npm install && cd ..Set VITE_API_URL=http://localhost:8000 in ui/.env.development.local. Add VITE_GOOGLE_MAPS_API_KEY only when location autocomplete is needed.4. Start the API in one terminal:bash.venv/bin/uvicorn application:app --reload --port 80005. Start the UI in a second terminal:bashcd uinpm run devOpen http://localhost:5174. The API is available at http://localhost:8000/docs.

License and pricing

Licensed under the Apache-2.0 license. The project is open source and free to use.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/guy-hartsteincompany-research-agent.svg)](https://yunodb.com/tools/guy-hartsteincompany-research-agent?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/guy-hartsteincompany-research-agent?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/guy-hartsteincompany-research-agent.svg" alt="Featured on YunoDB" height="20"></a>