CodeDox - AI-Powered Documentation Search & Code Extraction

Transform any documentation site into a searchable code database - CodeDox crawls documentation websites, intelligently extracts code snippets with context, and provides lightning-fast search via PostgreSQL full-text search and MCP (Model Context Protocol) integration for AI assistants.

📚 Documentation

For full documentation, installation guides, API reference, and more, visit:

https://chriswritescode-dev.github.io/codedox/

Quick Start

Docker Setup (Recommended)

# Clone the repository
git clone https://github.com/chriswritescode-dev/codedox.git
cd codedox

# Configure environment
cp .env.example .env
# Edit .env to add your CODE_LLM_API_KEY (optional for AI-enhanced extraction)

# Run the automated setup
./docker-setup.sh

# Access the web UI at http://localhost:5173
# MCP tools available at http://localhost:8000/mcp

Manual Installation

See the full installation guide for detailed instructions.

Key Features

Intelligent Web Crawling: Depth-controlled crawling with URL pattern filtering and domain restrictions
Smart Code Extraction: Dual-mode extraction (Automatic Title / Description or LLM Generated Titles and Descriptions)
Enhanced Search Modes: Standard code search with intelligent markdown fallback for comprehensive results
Lightning-Fast Search: PostgreSQL full-text search with fuzzy matching
GitHub Repository Processing: Clone and extract documentation from GitHub repositories with full path support (e.g., /tree/main/docs)
HTTP-First MCP Integration: MCP tools via HTTP endpoints with Streamable HTTP transport support (MCP 2025-03-26 spec)
Full Documentation Access: Get complete markdown content from any documentation page for full context
Modern Web Dashboard: React + TypeScript UI for visual management
Version Support: Track multiple versions of documentation
Real-time Monitoring: Live crawl progress and health monitoring
Upload Support: Upload documentation directly or from GitHub repositories (useful for repos with doc sites)