Local code intelligence MCP server and CLI for AI coding agents
-
Updated
May 20, 2026 - Rust
Local code intelligence MCP server and CLI for AI coding agents
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.
A Repository-Aware, Knowledge-Learning local MCP that understands your codebase in Real Time powered by Hybrid Semantic + Full-Text Engine, both supports claude code and codex
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.
MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.
A Repository-Aware, Self-Evolving Agent That Understands Codebase in Real Time powered by Hybrid Semantic + Full-Text Engine
Convert source code to LLM ready knowledge base
A semantic code search tool for intelligent, cross-repo context retrieval.
CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 42 MCP tools, 38 languages, a VS Code extension, and a persistent memory layer. AI agents get structured code understanding instead of grepping through files.
Go-based MCP server for codebase indexing and semantic search (Augment-compatible)
Give Claude Code a permanent memory — 100% local, zero config, graph-powered
Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code and OpenCode.
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-first Go service for AI agents, with MCP/REST APIs, bounded project indexing, workspace tools, and local Jira/Confluence ingestion
Local coding memory for AI agents. MCP-native. No LLM API required.
Self-hosted MCP server for hybrid semantic code search and repository intelligence.
Lightweight persistent memory for Claude Code — SQLite + FTS5, no daemon, no bloat. Session summaries, code indexing, task tracking, and contextual memory injection.
Enhanced fork of claude-context with stability fixes, improved sync, and better reliability for semantic code search
High-performance Rust MCP server that indexes codebases via vector + graph databases for AI coding agents
Intelligent code indexing MCP server. 13 tools, 10 languages, hybrid search, call graphs, O(1) symbol retrieval.
Add a description, image, and links to the code-indexing topic page so that developers can more easily learn about it.
To associate your repository with the code-indexing topic, visit your repo's landing page and select "manage topics."