A pip-installable CLI that fuses classic keyword search with semantic embeddings to find code the way you actually think about it.

Why I built it: I kept hunting for small pieces of code across large codebases and keyword search alone wasn't cutting it. AI tools could find it, but at a real cost in tokens for something a cheaper, purpose-built tool could do instead. So I built my own: chunking code, indexing it as vector embeddings, and combining semantic search with keyword matching to find what I was actually looking for.

• Built and packaged a pip-installable hybrid code search CLI, fusing BM25 keyword search with Voyage AI semantic embeddings via Reciprocal Rank Fusion to improve retrieval relevance over keyword or vector search alone.
• Designed a multi-language AST chunking pipeline with tree-sitter (Python, JavaScript, TypeScript/TSX), parsing source files into function- and class-level chunks for higher-precision embedding and retrieval.
• Implemented git-aware incremental indexing via a self-installing post-commit hook, re-embedding only changed files and safely extending a repo's existing hook interpreter (shell, Python, Node, Ruby).