coco-search
Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.
CocoSearch is a local-first hybrid semantic code search tool that combines vector similarity and keyword matching via RRF fusion. It uses CocoIndex for indexing, Tree-sitter for syntax-aware chunking, and PostgreSQL with pgvector for storage. It supports 32 languages, 9 grammars, dependency graphs, cross-repo search, and multiple interfaces.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- EElliot KimMay 25, 2026
Good for large codebases where keyword search misses semantically related code.
- SShawn KimApr 13, 2026
Hybrid semantic code search with PostgreSQL backing — better recall than pure vector search.
- Drew ChenMar 20, 2026
Local-first means code stays on your machine, important for proprietary projects.
- RRiley BrownMar 17, 2026
Indexes codebases fast enough that it stays current with active development.