Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.

Memory-aware context engine for AI coding agents — up to 91% fewer tokens, 17/18 rank-1 across 6 OSS projects. MCP-native, multi-repo, with persistent observations & decisions.

Local coding memory for AI agents. MCP-native. No LLM API required.

Intelligent code indexing MCP server. 13 tools, 10 languages, hybrid search, call graphs, O(1) symbol retrieval.

Python application to index code locally and support running server with indexed repos. Works with VoyageAI to power semantic searching a large codebase, enabling AI optimized code navigation. Supports FTS searching, and indexing git log. Experimental support for SCIP indexing.

Offline-first coding agent for local LLMs (LM Studio + MCP). Project-aware context, memory, and filesystem tooling for real coding workflows directly in your codebase.

Local context cache for LLM agents. 100% offline, zero dependencies.

An AI-powered system for intelligent code search, moving beyond keywords to semantic understanding. It offers multi-dimensional search capabilities across files, classes/interfaces, and methods, each with optimized AI-generated embeddings. Get precise, context-aware results to natural language queries quickly and efficiently.

Local semantic code search with Ollama embeddings, SQLite, and hybrid search. Index your codebase with language-aware chunking and find code by intent.

Pack 40+ files at 5 depth levels into any LLM context window. Keyword, semantic, and graph resolution. 100% recall at 1% of repo. Drop-in for any AI agent.

Semantic code maps for agents working across large repositories.

Codebase indexer powered by local LLM

🌲 Fast, reliable code intelligence — Tree-sitter AST parsing, contextual hybrid search, adaptive query planning, call-graph expansion & LLM synthesis. 20+ languages. Zero infra.

High-precision code context provider for AI agents. Bridges code_ast parsing with cocoindex-code for semantic chunking and local vector embeddings

Fast code map generator for AI coding assistants - Save 99%+ tokens while preserving context

Python script to extract a project metadata to analyze through SQL

Repository-local indexing for deterministic symbol lookup, semantic retrieval, and task-focused context for AI-assisted development across mixed-language repos, with pluggable language analyzers.

A very simple setup with pgvector, sentencetransformer, and MCP Python SDK, just to bootstrap indexing code files to facilitate RAG-based search for AI coding agents.

Nuke your token usage. Code indexing MCP server: 15 tools, 10 languages, O(1) retrieval, hybrid search, call graphs.