codebase-memory-mcp and mcp-codebase-index
These are direct competitors—both index codebases for efficient MCP-based search, but A emphasizes persistent knowledge graphs with broader language support while B focuses on structural navigation tools (functions, classes, dependency graphs) with lower barrier to adoption (zero dependencies, higher monthly downloads).
About codebase-memory-mcp
DeusData/codebase-memory-mcp
MCP server that indexes your codebase into a persistent knowledge graph. 64 languages, sub-ms queries, 99% fewer tokens than grep. Single Go binary, no Docker, no API keys.
Builds an AST-based knowledge graph using tree-sitter parsers with optional LSP-style type resolution for Go, C, and C++, persisting the graph to in-memory SQLite for sub-millisecond structural queries. Indexes codebases at extreme speed through RAM-first pipeline with LZ4 compression and fused Aho-Corasick pattern matching, completing the Linux kernel in 3 minutes. Implements the Model Context Protocol with 14 tools including architecture analysis, call graph tracing, impact mapping from git diffs, and Cypher-like graph queries—integrating with 10 coding agents (Claude Code, Zed, Gemini CLI, and others) through automatic MCP configuration on install.
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.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work