NA

nano-graphrag

Simple, hackable GraphRAG implementation in Python

Self-Hosted AI ★ 4k stars Medium setup MIT

nano-graphrag is a minimal, readable reimplementation of GraphRAG designed to be easy to understand and extend. It provides graph-based retrieval-augmented generation that can be embedded in self-hosted AI pipelines.

Key features

  • Minimal codebase
  • Easy to extend
  • Graph-based RAG
  • Pluggable storage

Strengths

  • Released under the MIT license
  • Active community (4k GitHub stars)
  • Written in Python

Is nano-graphrag secure?

OSV.dev has no published security advisories for nano-graphrag's repository. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

Source: OSV.dev, checked 2026-10-14. How this is measured.

nano-graphrag replaces

Health badge

Maintain nano-graphrag? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 47 · fair

Markdown
[![SelfHostIndex health score for nano-graphrag](https://selfhostindex.com/badge/nano-graphrag.svg)](https://selfhostindex.com/app/nano-graphrag/)
HTML
<a href="https://selfhostindex.com/app/nano-graphrag/"><img src="https://selfhostindex.com/badge/nano-graphrag.svg" alt="SelfHostIndex health score for nano-graphrag"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/nano-graphrag.svg
   :alt: SelfHostIndex health score for nano-graphrag
   :target: https://selfhostindex.com/app/nano-graphrag/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Similar self-hosted ai apps