codebase-memory-mcp and srclight
These are competitors offering different trade-offs: codebase-memory-mcp prioritizes lightweight indexing efficiency (sub-ms queries, single binary, 99% token reduction) while srclight offers richer analysis capabilities (call graphs, git blame, build system analysis, semantic search) at the cost of higher complexity.
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.
This tool helps developers understand their codebases more efficiently, especially when working with AI coding agents. It ingests your entire codebase, analyzing its structure across 66 programming languages, and outputs a persistent knowledge graph of functions, classes, and call chains. Developers, particularly those using AI agents for coding tasks, would use this to quickly query and visualize their project's architecture.
About srclight
srclight/srclight
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.
This helps AI coding assistants work faster and more effectively by providing a deep, searchable index of your codebases. It takes your source code and documentation files as input, instantly delivering precise answers to complex queries about code structure, relationships, and semantic meaning. Developers who use AI coding agents like Claude Code or Cursor will find this indispensable.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work