Agent Bletchley
An agentic web research system for investment due diligence.
Overview
Agent Bletchley is an intelligent research automation platform that leverages AI agents to conduct comprehensive web research for investment due diligence. The system uses OpenRouter's Tongyi DeepResearch model, integrated with Brave Search API and Jina Reader API to gather, analyze, and synthesize information from multiple sources.
Tech Stack
- Backend: Python 3.11, FastAPI, httpx (async HTTP), python-dotenv
- Frontend: Next.js 16 (App Router), TypeScript, Tailwind CSS, Framer Motion
- Database: Supabase (PostgreSQL)
- AI: OpenRouter API (for Tongyi DeepResearch)
- Tools: Brave Search API, Jina Reader API
- Deployment: Vercel (frontend + backend as serverless functions)
Project Structure
agent-bletchley/
├── backend/ # FastAPI backend application
├── frontend/ # Next.js frontend application
├── supabase/ # Database migrations
└── README.md # This file
Quick Start
Prerequisites
- Python 3.11+
- Node.js 18+
- Supabase account
- API keys for:
- OpenRouter API
- Brave Search API
- Jina Reader API
Backend Setup
- Navigate to the backend directory:
cd backend
- Create a virtual environment:
python -m venv venv
- Activate the virtual environment:
# On Windows PowerShell:
.\venv\Scripts\Activate.ps1
# On Windows Command Prompt:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate
- Install dependencies: