workflowstacks
mcp-server

code-graph-rag: AI‑powered search & edit for monorepos

Leverage code-graph-rag to query, understand, and modify multi‑language monorepos instantly. Ideal for founders building complex codebases. 5.2k+ GitHub stars.

From the repo · “The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs”

5,275 stars+17★ this week702 forksPythonGuide quality 9/10 · reviewed Oct 9Updated 10/22/2026100% 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

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
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/code-graph-rag && curl -fsSL https://workflowstacks.com/api/skills/code-graph-rag/claude-skill -o ~/.claude/skills/code-graph-rag/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How code-graph-rag: AI‑powered search & edit for monorepos works
Codeflow
Free to inspect

Code-graph-rag: AI‑powered search & edit for monorepos is a very large Python project (~144k lines across 409 code files, plus 925 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~144k lines · 409 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Python · Docker
Needs API keys (.env)
Python 99%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    main.py
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    examples/graph_export_example.py
    A worked example — copy this to get going
What's in each folder
codebase_rag/services/Backend / API12 files
codebase_rag/providers/Sub-packages / plugins3 files
docs/Documentation52 files
examples/Examples you can copy1 files
codebase_rag/parsers/Folder141 files
evals/Evaluations & benchmarks106 files
fuzz/Folder56 files
codebase_rag/analyzers/Folder47 files
READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
vitali87
Language
Python
Category
mcp-server
Published
6/16/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/code-graph-rag.svg)](https://workflowstacks.com/skills/code-graph-rag?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

MCP config

PostgreSQL MCP config

Let Claude run read-only queries against your Postgres database.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 355,695
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,361
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 131,266
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 17,935
WrenAI: Turn Natural Language into Trusted Dashboards & SQL
WrenAI lets founders ask plain‑language questions and instantly get reliable charts, dashboards, and SQL for 20+ data sources. Ideal for AI‑agent‑driven analytics teams. 18k+ GitHub stars.
mcp-server★ 5,709
openagent: Boost Founder Productivity with a Next‑Gen AI Assistant
openagent gives founders an AI‑powered personal assistant that can browse, code, and operate a computer using LLMs and RAG. Ideal for busy startup teams, it’s backed by 5.7k+ GitHub stars.
mcp-server★ 4,995
mockserver-monorepo: Rapid HTTP/HTTPS Mocking for Any Integration
Easily simulate external services and inspect traffic with Java, JavaScript, or Ruby clients—perfect for founders building reliable, test‑driven APIs. 5.0k+ GitHub stars.