Code Graph Rag

Code Graph Rag is an open-source tool that enables users to query, understand, and edit multi-language codebases with the power of AI and knowledge graphs. It uses a Tree-sitter based parser to read the codebase and ingests functions, classes, methods, modules, and their relationships into a graph under a single language-agnostic schema. The system has two components: a multi-language parser and a RAG system that turns natural language into Cypher queries, retrieves matching code, and drives AI-powered editing and optimisation. The graph is stored in an embedded SQLite file by default, but Memgraph and Neo4j are also available as opt-in backends. Code Graph Rag supports a wide range of languages, including Python, TypeScript, JavaScript, Rust, Go, Java, C, C++, and many others. It provides features such as code optimisation, dead code detection, dynamic call tracing, and graph export. The tool is designed to be used by developers, ML engineers, and data scientists who need to work with large and complex codebases. Code Graph Rag is available on GitHub and can be installed using pip or uv. It is licensed under the MIT license and has a strong focus on community involvement and contribution.

Category

Dev Tools

Pricing

Open Source

Official website: https://github.com/vitali87/code-graph-rag

Canonical LambdaBase page: https://www.lambdabase.com/tools/code-graph-rag