mcp-codebase-index and code-memory
These are complements: one provides precise structural navigation through AST-based queries while the other enables fuzzy semantic search through vector embeddings, addressing different code discovery needs within the same indexing workflow.
About mcp-codebase-index
MikeRecognex/mcp-codebase-index
17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.
Implements a streaming AST and regex-based parser with automatic git-aware incremental indexing—only changed files are reparsed, with built-in persistent caching via pickle that detects git HEAD mismatches and enables instant cold starts. Exposes Python, TypeScript, Go, Rust, and C# structural analysis (functions, classes, imports, callchains) as 18 MCP tools compatible with Claude Code and OpenClaw, eliminating file-reading overhead in large codebases.
About code-memory
kapillamba4/code-memory
MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.
Implements a three-tier retrieval strategy (BM25 + dense vectors via SQLite-vec + AST parsing) across specialized tools that route queries by type—code definitions, architectural documentation, and Git history—powered by local sentence-transformers embeddings. Integrates as an MCP server with Claude Desktop, VS Code (Copilot/Continue), Gemini CLI, and Claude Code, supporting 8 languages with full AST extraction and 9+ with fallback whole-file indexing.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work