Back to directory

cocoindex-code

A lightweight, AST-based semantic code-search CLI, built on a Rust data-transformation engine, that lets a coding agent find and fetch relevant code without reading whole files.

cocoindex-code

cocoindex-code is a lightweight semantic code-search tool built on tree-sitter AST parsing and CocoIndex, a Rust-based data-transformation engine. It indexes a codebase once and then answers searches with the specific symbols and context a query needs, aiming to cut the number of tokens a coding agent spends reading through irrelevant file content by a large margin.

It can be used directly from the command line or integrated with Claude, Codex, Cursor, or another coding agent through a skill or an MCP server, and installs with either a batteries-included variant that bundles local sentence-transformer embeddings needing no API key, or a slim variant that relies on a cloud embedding provider. A single plugin marketplace ships the skill, optional hooks, and the MCP server together under one plugin id for both Claude Code and Grok.

It is written in Python and released under the Apache License 2.0.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.