codebase-memory-mcp and CodeMCP

codebase-memory-mcp
63
Established
CodeMCP
44
Emerging
Maintenance 25/25
Adoption 10/25
Maturity 9/25
Community 19/25
Maintenance 13/25
Adoption 9/25
Maturity 9/25
Community 13/25
Stars: 585
Forks: 65
Downloads:
Commits (30d): 317
Language: C
License: MIT
Stars: 71
Forks: 9
Downloads:
Commits (30d): 0
Language: Go
License:
No Package No Dependents
No Package No Dependents

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 CodeMCP

SimplyLiz/CodeMCP

Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping

Leverages SCIP-based semantic indexing to build cross-file call graphs and dependency analysis—currently supporting Go (Tier 1), TypeScript/JavaScript/Python (Tier 2), and other languages with varying feature completeness. The tool operates through three interfaces: MCP (Model Context Protocol) for seamless integration with Claude and other AI assistants, a CLI for direct terminal queries, and an HTTP API for CI/CD pipelines and custom tooling. Features include semantic call graph navigation, blast radius calculation with risk scoring, dead code detection, ownership tracking via CODEOWNERS analysis, and automated secret scanning with 26 patterns—all designed to reduce token usage by 83% through smart preset loading.

Scores updated daily from GitHub, PyPI, and npm data. How scores work