Tech News
← Back to articles

Show HN: ChunkHound, a local-first tool for understanding large codebases

read original related products more articles

Local first codebase intelligence

Your AI assistant searches code but doesn't understand it. ChunkHound researches your codebase—extracting architecture, patterns, and institutional knowledge at any scale. Integrates via MCP.

Features

cAST Algorithm - Research-backed semantic code chunking

- Research-backed semantic code chunking Multi-Hop Semantic Search - Discovers interconnected code relationships beyond direct matches

- Discovers interconnected code relationships beyond direct matches Semantic search - Natural language queries like "find authentication code"

- Natural language queries like "find authentication code" Regex search - Pattern matching without API keys

- Pattern matching without API keys Local-first - Your code stays on your machine

- Your code stays on your machine 30 languages with structured parsing Programming (via Tree-sitter): Python, JavaScript, TypeScript, JSX, TSX, Java, Kotlin, Groovy, C, C++, C#, Go, Rust, Haskell, Swift, Bash, MATLAB, Makefile, Objective-C, PHP, Vue, Svelte, Zig Configuration : JSON, YAML, TOML, HCL, Markdown Text-based (custom parsers): Text files, PDF

with structured parsing MCP integration - Works with Claude, VS Code, Cursor, Windsurf, Zed, etc

... continue reading