code-graph-rag

code-graph-rag

A multilingual codebase querying and editing system based on knowledge graphs.

MCPDevOpen sourceRAG知识图谱代码分析
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 2.3k
Source
mcp-github

Overview

Code-Graph-RAG is a powerful Retrieval-Augmented Generation (RAG) system capable of analyzing multilingual codebases and building comprehensive knowledge graphs. It uses Tree-sitter for robust, language-agnostic abstract syntax tree parsing and supports multiple programming languages. Through natural language queries, AI can understand codebase structure and relationships, enabling editing operations. Ideal for developers managing and maintaining large multilingual codebases.

Capabilities

  • Multilingual codebase analysis
  • Knowledge graph construction
  • Natural language query of codebases
  • Code editing capabilities

Use cases

Codebase structure queryingUnderstanding code relationshipsCode editing and refactoringMultilingual code management

Setup

Requires: API KeyNode 环境
pip install code-graph-rag

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

What programming languages are supported?

Supports C, C++, Java, JavaScript, Lua, PHP, Python, Rust, and TypeScript, among others.

How do I get started?

After installation, configure your API key and run the example code.

Related skills