code-review-graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked contex
Star Growth
Overview
Builds a structural map of a codebase using Tree-sitter and serves compact context over MCP to AI coding assistants. It integrates with platforms like Cursor, Claude Code, and Cline to reduce the context they need to read. The tool installs MCP servers and hooks to keep the graph updated incrementally.
Deep Analysis
Provides AI coding tools with a local, persistent structural map of the codebase to drastically reduce the context they need to read.
⚡ Capabilities
- • Builds a persistent AST-based map of a codebase
- • Serves context to AI coding tools via MCP
- • Incrementally updates the graph
- • Integrates with multiple AI coding platforms
🔗 Integrations
✓ Best For
- ✓ Reducing context size for AI code reviews
- ✓ Improving AI coding tool performance on large repositories
- ✓ Providing precise code change context to assistants
✗ Not Ideal For
- ✗ End-user chatbot creation
- ✗ Generic AI content generation
- ✗ Non-AI development tools
⚠ Known Limitations
- ⚠ Requires Python 3.10+
- ⚠ Initial build time scales with repository size
- ⚠ Partial parse failures leave some files unprocessed
Alternatives
Works with code-review-graph
Tools that integrate with code-review-graph, often used together in the same stack.
Compare code-review-graph
Maintain code-review-graph?
Show your live rank in your README, or put code-review-graph in front of every visitor to AgentoolRank.