codebase-memory-mcp vs code-review-graph

Local code graphs for AI coding tools compared

Both projects build local, persistent code graphs to give AI coding tools focused repository context through MCP or command-line workflows. codebase-memory-mcp emphasizes code navigation and structural queries, while code-review-graph focuses on change impact and review context, including pull request automation.

codebase-memory-mcpcode-review-graph
LanguageCPython
LicenseMITMIT
Stars45.7k31.9k
Forks3.8k2.9k
Last analyzedOct 3, 2026Oct 3, 2026

Key differences

  • codebase-memory-mcp indexes definitions, calls, imports, routes, and types; code-review-graph also extracts inheritance and test relationships for review context.
  • codebase-memory-mcp uses bundled Tree-sitter grammars with Hybrid LSP semantic type resolution for supported languages; code-review-graph uses Tree-sitter and other targeted parsers, with custom language mappings available.
  • code-review-graph includes a GitHub Action for risk-scored pull request comments; codebase-memory-mcp offers an optional browser-based graph visualization UI.
  • Both store graph data locally in SQLite, but code-review-graph also supports optional external embedding providers, which receive source-derived text when used.
  • codebase-memory-mcp is written in C, while code-review-graph is written in Python and requires Python 3.10 or newer.
  • Both use the MIT license; codebase-memory-mcp has 45.7k stars and 3.8k forks, compared with 31.9k stars and 2.9k forks for code-review-graph. Both are unarchived.

Choose codebase-memory-mcp if you…

  • want agents to trace code relationships, search structurally, or summarize architecture through graph queries.
  • need route-to-call relationships or links across services and repositories.
  • want a local MCP server with an optional browser-based graph visualization UI.
Read the codebase-memory-mcp analysis →

Choose code-review-graph if you…

  • need review context that traces potential impact through callers, dependents, and tests.
  • want a CLI for graph updates, change inspection, dead-code searches, or visualization exports.
  • want to post risk-scored pull request review comments through a GitHub Action.
Read the code-review-graph analysis →

Compare the numbers side by side, or add more projects

This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.