IntermediatePython

code-graph-ragOpen-source RAG system leveraging knowledge graphs and LLMs for monorepos

code-graph-rag is an open-source RAG system that leverages knowledge graphs and large language models (LLMs) to navigate complex, multi-language monorepos. It enables natural language queries, deep code understanding, and editing across vast codebases, helping developers manage intricate projects more efficiently. The project is primarily written in Python and is licensed under the MIT License. As of collection time, it has 2,333 stars on GitHub.

2.3K Stars

391 Forks

18 Issues

241 Views

Python

MIT

IndexedJuly 21, 2026

GitHub repository Online Demo

Project Overview

code-graph-rag is an open-source RAG (Retrieval-Augmented Generation) system designed for complex, multi-language monorepos. It combines knowledge graphs with large language models to provide natural language querying, deep code comprehension, and editing capabilities, helping developers navigate and manage large codebases effectively.

Core Features

Uses knowledge graphs to organize code structure, enabling efficient retrieval.
Integrates LLMs to support natural language interaction.
Supports cross-language code understanding, ideal for multi-language monorepos.
Offers code editing capabilities to assist developers in modifications.

Technology Stack

The primary programming language is Python.

License

The project is released under the MIT License.

Community and Status

As of collection time, the project has 2,333 stars on GitHub (this number is a snapshot and may vary over time).

code-graph-ragknowledge graph RAGcode query toolmulti-language codebaseopen-source RAGmonorepo managementAI coding assistantgraph databasenatural language code querycode understanding tool

Project Rating

0.0 (0 Reviews)

Frequently Asked Questions

What is code-graph-rag: Open-source RAG system leveraging knowledge graphs and LLMs for monorepos?

What language is code-graph-rag: Open-source RAG system leveraging knowledge graphs and LLMs for monorepos written in?

code-graph-rag: Open-source RAG system leveraging knowledge graphs and LLMs for monorepos is primarily written in Python.

What license is code-graph-rag: Open-source RAG system leveraging knowledge graphs and LLMs for monorepos under?

code-graph-rag: Open-source RAG system leveraging knowledge graphs and LLMs for monorepos is released under the MIT license.

Related Projects

No results yet

Explore More

Similar Tools

doc2mcp

doc2mcp converts any documentation URL (Stripe, your own API, internal wikis) into a hosted, token-secured MCP server in seconds. Each page becomes typed tools that Cursor, Claude, Windsurf, and VS Code can search and cite, ensuring answers come from real docs rather than hallucinations. Use it via web or terminal with npx doc2mcp.

AI Coding Nav

A lightweight Chinese-language navigation page on Cloudflare Pages that catalogs AI tools across the software development workflow, framed as a 2026 map of the AI coding stack.

Stellar AI

Stellar AI is an AI script generator tailored for game developers, specializing in FiveM's QBCore/ESX frameworks and the Roblox platform. It bypasses complex prompts, generating complete Lua scripts with fxmanifest from everyday English descriptions. It can also fix broken code. A free tier is available, with paid subscriptions starting from £10/month.

Bugpilot

Bugpilot is a browser extension built for vibe coders using Claude and ChatGPT. It captures the entire browser in one click, including console errors with stack traces, network requests, DOM state, clicks, and screenshots, then exports it as clean, AI-ready Markdown. 100% local: no servers, no accounts, no telemetry, always-on redaction. Pro adds React component state, 5 AI-optimized export formats, and unlimited history. Free forever, $28 one-time, 14-day refund, no subscription.

AuraIntel

AuraIntel is a real-time AI coding assistant designed as a desktop overlay, claiming to be undetectable during Zoom, Teams, or Discord screen shares. It captures problems, generates code, and automatically types solutions at the cursor, specifically targeting programming interviews. However, official technical details and pricing remain undisclosed, and its stealth design raises significant academic integrity concerns.

Penling

Penling is an agentic spec-driven workflow tool designed to bring team collaboration to the forefront of AI-assisted development. It enables teams to collectively define specifications in a shared workspace, then leverages AI to generate code and produce review-ready pull requests. Moving spec documents from individual CLI tools to a collaborative environment, Penling supports Google, Microsoft, and GitHub logins, offering a 14-day free trial.