code-graph-rag
A multilingual codebase querying and editing system based on knowledge graphs.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 2.3k
- Source
- mcp-github
- Repository
- github.com/vitali87/code-graph-rag
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
Setup
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
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
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.