Local-first hybrid semantic code search with pgvector + Ollama embeddings. CLI, MCP server, and web dashboard for 30+ languages.
Coco-Search is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view VioletCranberry/coco-search --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 149 days ago.
45 GitHub stars indicate community interest.
3 open issues signal maintenance load.
MIT license detected.
2 security/trust notes recorded.
Setup difficulty is 3/5.
Codebase intelligence layer for AI coding agents: code health, git analytics, dead code detection, and architectural decisions via MCP.
Deep code indexing MCP server for AI agents with hybrid FTS5 + embedding search, call graphs, and multi-repo workspaces.
A project template that turns your repository into stable infrastructure for AI-assisted development.
Local code intelligence MCP server and CLI for AI coding agents, providing semantic search and call graph analysis.
Coco-Search gives AI agents semantic understanding of your codebase — they can find relevant code by meaning, not just keywords. It combines traditional search with vector embeddings for highly accurate results across 30+ programming languages.
Coco-Search is a local-first code search engine built for AI coding workflows. It uses pgvector for storing embeddings and Ollama for generating them locally. Features include a CLI, MCP server integration (so AI agents can search your code directly), and a web dashboard. Supports over 30 programming languages with semantic understanding.
45
Stars
5
Forks
3
Issues
MIT
License
Local-first hybrid semantic code search with pgvector + Ollama embeddings. CLI, MCP server, and web dashboard for 30+ languages.
Software Engineers, AI-assisted Developers
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Runs locally — no code leaves your machine Requires PostgreSQL with pgvector extension
Similar or complementary options to evaluate include repowise, srclight, attractor-guided-engineering-template.
Aug 20, 2026