Introduction
Codebase Memory MCP is the fastest code-intelligence engine for AI coding agents, with 1,300+ GitHub stars. Millisecond-scale indexing for typical repos; 3 minutes for the Linux kernel (28M lines, 75K files). Built on tree-sitter AST parsing with support for 66 programming languages and sub-millisecond graph queries. Ideal for developers using MCP clients like Claude Code and Cursor.
Codebase Memory MCP — Full Code Intelligence Engine
Core Features
- 66 languages — JS, Python, Go, Rust, Java, C++, and more
- Sub-ms queries — knowledge graph backed by SQLite
- 14 MCP tools — search, tracing, architecture analysis, dead-code detection
- 3D graph visualization — built-in UI to explore code relationships
- Git diff impact analysis — understand the blast radius of code changes
- Single-file binary — zero dependencies, download and run
Performance Benchmarks
| Codebase | Files | Lines | Indexing Time |
|---|---|---|---|
| Typical project | ~500 | ~50K | < 1s |
| Large monorepo | ~5,000 | ~500K | ~30s |
| Linux kernel | 75,000 | 28M | ~3 min |
FAQ
Q: What is Codebase Memory MCP? A: A high-performance MCP server that indexes entire codebases into a queryable knowledge graph, giving AI agents deep understanding of code structure.
Q: Is it free? A: Completely free and open source under the MIT license.