// Read docs & web pages
graphragv3.3.0
A modular graph-based Retrieval-Augmented Generation (RAG) system
Open source Maintained For agents
IN ONE PARAGRAPH
graphrag is A modular graph-based Retrieval-Augmented Generation (RAG) system.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to read docs & web pages.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it from the official package registry:
pip install graphrag - 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side → LightRAG [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation ★ 40k trafilatura Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML ★ 7.0k Vane Vane is an AI-powered answering engine. ★ 38k Scrapegraph-ai Python scraper based on AI ★ 32k crawl4ai Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. ★ 86k