vitali87 / code-graph-rag

TL;DR

Code-Graph-RAG is a tool that parses multi-language codebases using Tree-sitter, creating a knowledge graph for querying and editing code in plain English. It supports Ruby and enables structural search and replace across various programming languages.

✦ Why It Matters

Start using Code-Graph-RAG today to simplify codebase management and enhance code quality through natural language queries.

Key Takeaways

Utilize Code-Graph-RAG for multi-language codebase analysis.
Leverage natural language queries for code retrieval and editing.
Implement structural search and replace with AST patterns.
Track data flows across assignments and function calls.

How It Works

Code-Graph-RAG employs Tree-sitter to parse source code into an Abstract Syntax Tree (AST), which is then transformed into a knowledge graph stored in Memgraph. This graph allows for complex queries and interactions, enabling users to ask questions about their code in natural language.

The system's architecture facilitates seamless integration of various programming languages, making it versatile for developers working in diverse environments.

vitali87 / code-graph-rag

BerriAI / litellm

tensorflow / tensorflow

open-webui / open-webui

Agentic data science with the Data Agent Kit

BerriAI / litellm

tensorflow / tensorflow

open-webui / open-webui

Agentic data science with the Data Agent Kit