mcp-server

code-graph-rag: AI code insights

Name: code-graph-rag: AI code insights
Author: vitali87

Get AI-powered code analysis for your monorepo with code-graph-rag, used by developers with 2.3k+ GitHub stars

2,317 stars385 forksPythonQuality 8/10Updated 7/15/2026100% free · open source

What it does

Code-graph-rag analyzes your monorepo's codebase using AI and knowledge graphs, allowing you to query, understand, and edit multi-language codebases

Install / run

pip install code-graph-rag

When to use it

•You have a large, complex monorepo with multiple languages and need help understanding the relationships between components
•You want to automate code reviews and ensure consistency across your codebase
•You need to refactor or optimize your codebase, but struggle to identify the best places to start

Quick start

1Clone the code-graph-rag repository with `git clone https://github.com/vitali87/code-graph-rag.git`
2Change into the repository directory with `cd code-graph-rag`
3Create a new configuration file with `cp config.example.yaml config.yaml` and edit it to match your monorepo's structure
4Run the code-graph-rag server with `python -m code_graph_rag.server`
5Use the code-graph-rag client to query your codebase, such as `python -m code_graph_rag.client --query 'SELECT * FROM functions'`

Ready-to-paste prompt

python -m code_graph_rag.client --query 'SELECT * FROM functions WHERE language = "python"'

Heads up: Make sure you have Python 3.8 or later installed, as code-graph-rag relies on features introduced in this version

Saves to your device

Topics

ast

claude-code

code-analysis

code-understanding

codebase-search

developer-tools

graph-database

knowledge-graph

llm

mcp

mcp-server

memgraph

monorepo

multi-language

python

rag

retrieval-augmented-generation

semantic-search

tree-sitter

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

65.3M

repo size

MIT

license

Key files

.pre-commit-config.yaml

main.py

PYPI_README.md

README.md

File tree

.github/

.vscode/

assets/

benchmarks/

cgr/

codebase_rag/

codec/

docs/

evals/

examples/

optimize/

scripts/

.dockerignore

.env.example

.gitignore

.gitmodules

.pre-commit-config.yaml

.python-version

build_binary.py

code-graph-rag-darwin-arm64.spec

CONTRIBUTING.md

Dockerfile

funding.json

LICENSE

Quick Actions

Details

Creator

vitali87

Language

Python

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 207,966

ECC: Optimize Performance

Get optimized performance with ECC, a research-first agent harness system for founders working with AI agents and developer tools like Claude Code and Codex, with 203k+ GitHub stars.

mcp-server★ 156,712

JavaGuide: Ace Back-End Interviews

Get comprehensive Java interview prep for startup founders, with 156k+ GitHub stars.

mcp-server★ 148,885

Dify: Streamline Workflow

Get a production-ready platform with Dify. For founders needing agentic workflow development.

mcp-server★ 145,485

open-webui: Easy AI Interface

Get a user-friendly AI interface with open-webui, supporting Ollama and OpenAI API, for founders, with 145k+ GitHub stars

mcp-server★ 104,971

gemini-cli: AI in your terminal

Get AI power with gemini-cli, for founders, 105k+ GitHub stars

mcp-server★ 88,612

awesome-mcp-servers

Get a collection of MCP servers for AI development, for founders and developers.