ai-agent

graphrag: Smarter AI Agents

Name: graphrag: Smarter AI Agents
Author: microsoft

Get modular graph-based Retrieval-Augmented Generation with graphrag, ideal for founders working with GPT and LLMs

advanced⏱ 1-2 hours💵 Free + LLM API costs

36,060 stars+23★ this week (early data)3,796 forksPythonGuide quality 8/10 · reviewed Jun 5Updated 9/21/2026100% free · open source

What it is

Build smarter AI agents using graphrag, a system that helps generate text based on information from a graph (a type of data structure) (data arrangement method)

Real use case example

"A founder of an e-commerce company wants to build a chatbot that can answer customer questions about products, so they use graphrag to create a graph of product information, then use GPT to generate human-like responses, and finally deploy the chatbot on their website, resulting in a more informed and satisfied customer base"

When to use it

•Analyzing large volumes of text documents for research and competitive intelligence
•Breaking down complex industry reports or market research into digestible insights
•Creating comprehensive knowledge bases from scattered information sources

Ready-to-paste prompt

graphrag analyze --input market_reports/ --output insights.json --model gpt-4

Saves to your device

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/graphrag && curl -fsSL https://workflowstacks.com/api/skills/graphrag/claude-skill -o ~/.claude/skills/graphrag/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 graphrag: Smarter AI Agents works

Codeflow

Free to inspect

Graphrag: Smarter AI Agents is a large Python project (~36k lines across 456 code files, plus 124 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Large codebase

~36k lines · 456 code files · ~5 h to skim

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python

No API keys detected

Python 88%Jupyter Notebook 12%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes

What's in each folder

packages/Sub-packages / plugins485 files

docs/Documentation105 files

unified-search-app/Folder34 files

scripts/Helper scripts8 files

tests/Tests — proof it works187 files

.semversioner/Tool / agent settings44 files

.github/CI / automation (GitHub Actions)18 files

.vscode/Editor / agent settings3 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/graphrag && curl -fsSL https://workflowstacks.com/api/skills/graphrag/claude-skill -o ~/.claude/skills/graphrag/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.

Quick Actions

Details

Creator

microsoft

Language

Python

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.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.