Code Review Graph
Open-sourceBuilds a persistent knowledge graph of your codebase so AI reads only what matters — reducing review tokens by up to 49x.
About Code Review Graph
Code Review Graph builds a persistent knowledge graph of your codebase to help AI tools like Claude Code read only relevant code. This Python-based tool reduces token usage by up to 49x during daily coding tasks and 6.8x during code reviews.
Best For
- Large codebase analysis with AI assistance
- Reducing AI coding costs through efficient context management
Pros & Cons
Pros
- + Dramatically reduces token usage in AI code reviews
- + Persistent graph avoids re-analyzing unchanged code
- + Open source with 12.6k GitHub stars
Cons
- - Primarily focused on Claude Code integration
- - Initial codebase indexing may take time for large repos
Pricing
Open source and free to use
Key Features
- Persistent knowledge graph for efficient codebase navigation
- Reduces token usage up to 49x in daily coding tasks
- Tree-sitter integration for accurate code analysis
- MCP server support for Claude Code integration
Similar Tools
Related AI Tools
vLLM
High-throughput and memory-efficient inference and serving engine for production LLM deployments.
LlamaFactory
Unified framework for efficient fine-tuning of 100+ LLMs and VLMs with no-code and CLI interfaces.
LiteLLM
Python SDK and proxy server to call 100+ LLM APIs in OpenAI format with cost tracking and load balancing.
Browser Use
Open-source AI agent that automates web tasks by making websites accessible to AI with browser control.
Skyvern
Automate browser-based workflows with AI-powered visual understanding and multi-library support.
GraphRAG
Microsoft's modular graph-based RAG system for enhanced LLM outputs through knowledge graph integration.