codebase-search

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

Turning messy repos into weapons of mass structured context.

🕸️ Code knowledge graph for Claude Code & AI coding agents — index TypeScript, NestJS, React into Neo4j and query architecture in Cypher

Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdrant + local llama.cpp embeddings. Your code never leaves your machine. MIT.

Give coding agents trustworthy, cited answers about your codebase. Code graph + MCP server, no LLM required.

Turn your codebase into a knowledge graph. 11 MCP tools for AI code assistants — search, impact analysis, shortest path, semantic similarity, and more.

Intelligent codebase context engine for AI coding agents. Semantic RAG from source code via MCP tools.

mind readingly accurate, blazingly fast codebase search, written in pure rust.

Agentic RAG developer copilot: ask your codebase, commits, PRs and issues. Groq + Gemini, hybrid search, installable PWA.

Your coding agent is smart. Your legacy codebase is the problem. Reify gives it the context to understand and safely change large, unfamiliar codebases — 100% locally.

Local, deterministic code intelligence for developers and AI coding assistants — cited answers about symbols, callers, references, routes, and change impact, without dumping your repo into a context window.

Cloudflare AI Search toolkit: MCP server, streaming /ask Worker, docs widget, and git-to-R2 corpus sync. AGPL.

🧠 MCP server for semantic code search, cross-chat memory & token-slim routing — cut LLM token usage 80-95%. 100% local, no API keys. Works with Claude Code, Cursor, Codex, Hermes.

100% offline, privacy-first local RAG search and chat engine for codebases and documents. Pure SQLite hybrid storage (FTS5 BM25 + dense vector embeddings) with zero cloud fees.

Local-first, agentic coding workspace for Ollama and OpenAI-compatible models. Multi-project dashboard, three-pane editor, VS Code-style terminal, semantic codebase search (RAG), Git-aware editing with checkpoints, skills, persistent memory, and hardened per-tool approval — all running on your machine.

Local, API-free RAG assistant that lets you chat with any codebase — AST-aware chunking, Ollama embeddings/LLM, Chroma vector store, multi-repo switching, FastAPI + chat UI.

RAG-powered assistant that ingests any GitHub repo and answers natural-language questions about the codebase using LangChain + GPT-4o

Open-source codebase intelligence you can self-host. Real AST + dependency graph + grounded retrieval. AGPL-3.0. Built for devs priced out of enterprise tooling.

AI-powered coding assistant that understands YOUR codebase. Get answers, generate tests, refactor code.

7-Stage Local RAG Engine over Codebases — Crawler, Chunker, Embedder, VectorIndex, Retriever, ContextPacker, AnswerSynthesizer. ~3200 LOC. MiMo + Hermes.