nano-graphrag
Simple, hackable GraphRAG implementation in Python
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
nano-graphrag replaces
Compare nano-graphrag
10 head-to-head comparisons.
Similar self-hosted ai apps
OpenClaw
Self-Hosted AIThe AI that actually does things
Hermes Agent
Self-Hosted AIThe AI agent that grows with you
OpenCode
Self-Hosted AIThe open source AI coding agent
Hugging Face Transformers
Self-Hosted AIState-of-the-art machine learning model library
Replaces OpenAI API
Langflow
Self-Hosted AIVisual framework for building AI agents and RAG pipelines
Replaces Vertex AI Agent Builder
Dify
Self-Hosted AIOpen-source platform for building production LLM apps
Replaces OpenAI Assistants, Vertex AI Agent Builder