Transform AI coding assistants from guessing to knowing. ChunkHound enables deep, iterative exploration that understands your complete engineering context - code, architecture, patterns, and written knowledge.

The Reality

Your AI assistant helps you code but lacks critical context: Missing code context • Duplicate functions • Breaking patterns • Lost architecture • Conflicting specs • Scale overwhelm

ChunkHound gives AI the context it needs - deep understanding of your code, files, and architectural decisions before writing anything.

What is Deep Research for Code & Files?

Just like Deep Research transforms how you explore the web, ChunkHound and the Code Expert brings Deep Research to your local codebase and files. Search across 22+ file types including Python, JavaScript, TypeScript, Markdown, PDFs, and more.

• Iterative Discovery - Start with a concept, expand through code, markdown files, and comments
• Multi-hop Search - Find connections between implementation and written knowledge
• Architecture Map - Understand relationships across code files, README files, and design notes
• Complete Context - Find that validateEmail() AND the markdown file explaining why it exists

Production Ready

Battle-tested at scale:

• Handles codebases from thousands to millions of lines
• 22 programming languages with full parsing support
• 5 minutes from installation to first search
• Zero cloud dependencies - runs entirely local

Built on proven foundations:
Tree-sitter for parsing • DuckDB for local storage • MCP for AI integration

Stop recreating code. Start with deep understanding.

Latest Updates

Stay up to date with ChunkHound's latest features and improvements.

Recent Improvements

🚀

Multi-hop semantic search, automatic file watching, and enhanced MCP server reliability.

• Enhanced parsing with universal language support
• Improved MCP server coordination and watchdog
• Simplified configuration for easier setup

Performance Boost

⚡

Significant performance improvements and reliability enhancements.

• Enhanced database portability with relative paths
• Better file change processing and debouncing
• Improved MCP server initialization

Enhanced Features

✨

New transport options and improved development experience.

• MCP HTTP transport alongside stdio support
• Unified configuration across CLI and MCP
• Better cross-platform file path handling

View Full Changelog →