code-review-graph
Code review graph for AI coding tools, providing precise context.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 18.8k
- Source
- mcp-github
- Repository
- github.com/tirth8205/code-review-graph
Overview
code-review-graph is a locally-first code intelligence graph designed for MCP and CLI. It builds a persistent codebase map that enables AI coding tools to read only relevant parts, significantly reducing context in code reviews and large repository workflows. By parsing the codebase with Tree-sitter and tracking incremental changes, code-review-graph delivers precise context to AI assistants via the MCP protocol. Ideal for developers requiring efficient code reviews.
Capabilities
- ▪Build codebase structure graph
- ▪Track incremental code changes
- ▪Provide precise context via MCP
- ▪Reduce context overhead in code reviews
Use cases
Setup
pip install code-review-graph or pipx install code-review-graph; code-review-graph install; code-review-graph build
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I install?
Install using pip or pipx, then run the initialization command.
Which platforms are supported?
Supports Codex, Cursor, Claude Code, and others.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
antivibe
Transform AI-generated code into deep learning materials to help developers understand the code.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.