# Company Research Agent: Deep Diligence with Multi-Agent AI and LangGraph

This repository profile is provided by osrepos.com, an open source repository discovery platform.

Source: osrepos.com
Repository profile: https://osrepos.com/repo/guy-hartstein-company-research-agent
Generated for open source discovery and AI-assisted research.

The Company Research Agent is an advanced tool designed for in-depth company diligence, leveraging a multi-agent framework built with LangGraph and Tavily. It efficiently gathers, filters, and synthesizes information from various sources. The system utilizes Google's Gemini 2.5 Flash for high-context synthesis and OpenAI's GPT-5.1 for precise formatting, delivering comprehensive research reports.

GitHub: https://github.com/guy-hartstein/company-research-agent
OSRepos URL: https://osrepos.com/repo/guy-hartstein-company-research-agent

## Summary

The Company Research Agent is an advanced tool designed for in-depth company diligence, leveraging a multi-agent framework built with LangGraph and Tavily. It efficiently gathers, filters, and synthesizes information from various sources. The system utilizes Google's Gemini 2.5 Flash for high-context synthesis and OpenAI's GPT-5.1 for precise formatting, delivering comprehensive research reports.

## Topics

- agents
- ai
- company
- financial-analysis
- gemini
- langgraph-python
- multi-agent-systems
- openai

## Repository Information

Last analyzed by OSRepos: Tue Feb 03 2026 00:00:26 GMT+0000 (Western European Standard Time)
Detail views: 9
GitHub clicks: 4

## Safety Notice

OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything.

## Content

## Introduction

The `company-research-agent` is an innovative open-source project that provides an agentic solution for conducting deep diligence on companies. Built on a multi-agent framework using LangGraph, it automates the process of gathering, curating, and synthesizing information from diverse sources. The tool integrates powerful AI models, specifically Google's Gemini 2.5 Flash for extensive research synthesis and OpenAI's GPT-5.1 for refined report generation and formatting, ensuring both comprehensive content and polished presentation.

Key features include multi-source research capabilities, AI-powered content filtering using Tavily's relevance scoring, and a modular architecture with specialized research and processing nodes. The project also boasts a modern React frontend for an intuitive user experience, complete with progress tracking and report download options.

## Installation

Getting started with the Company Research Agent is straightforward, with options for quick setup, manual installation, or Docker deployment.

### Quick Installation (Recommended)

1.  **Clone the repository**:
    bash
    git clone https://github.com/guy-hartstein/company-research-agent.git
    cd company-research-agent
    
2.  **Run the setup script**:
    bash
    chmod +x setup.sh
    ./setup.sh
    
    This script will handle Python and Node.js dependencies, create a virtual environment, and guide you through environment variable setup. It also supports `uv` for faster package installation.

### Docker Installation

1.  **Clone the repository**:
    bash
    git clone https://github.com/guy-hartstein/company-research-agent.git
    cd company-research-agent
    
2.  **Configure Environment Variables**:
    Create a `.env` file in the project root for backend keys and a `ui/.env` file for frontend keys. You'll need API keys for Tavily, Google Gemini, OpenAI, and Google Maps.
3.  **Build and start containers**:
    bash
    docker compose up --build
    
    The backend will be available at `http://localhost:8000` and the frontend at `http://localhost:5174`.

## Examples

Once installed, you can run the application locally to perform company research.

1.  **Start the backend server** (in the project root):
    bash
    uvicorn application:app --reload --port 8000
    
    or
    bash
    python -m application.py
    
2.  **Start the frontend development server** (in the `ui` directory):
    bash
    cd ui
    npm run dev
    
3.  **Access the application** in your browser at `http://localhost:5173`. You can then input a company name and initiate a research report, observing the multi-agent system at work.

An [online demo](https://companyresearcher.tavily.com) is also available to try out the functionality directly.

## Why Use

The Company Research Agent offers several compelling advantages for anyone needing deep, automated company insights:

*   **Comprehensive Research**: It gathers data from a multitude of sources, including company websites, news articles, and financial reports, providing a holistic view.
*   **Intelligent Content Filtering**: Leveraging Tavily's AI-powered relevance scoring, it ensures that only the most pertinent information is included in the final report, saving time and improving accuracy.
*   **Optimized AI Architecture**: By using Gemini 2.5 Flash for high-context synthesis and GPT-5.1 for precise formatting, the tool combines the strengths of leading AI models for superior output quality.
*   **Modular and Scalable**: Its LangGraph-based multi-agent framework allows for specialized processing, making it robust and adaptable for future enhancements.
*   **User-Friendly Interface**: The modern React frontend provides a responsive and intuitive experience, making complex research accessible to all users.

## Links

*   **GitHub Repository**: [https://github.com/guy-hartstein/company-research-agent](https://github.com/guy-hartstein/company-research-agent){:target="_blank"}
*   **Online Demo**: [https://companyresearcher.tavily.com](https://companyresearcher.tavily.com){:target="_blank"}