gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation
This project helps you understand complex documents by turning raw text into a connected knowledge graph. It takes your documents, extracts key information and relationships, and then lets you ask questions to get concise, contextually rich answers. Anyone who needs to extract insights and query large amounts of text data, like researchers, analysts, or content strategists, will find this useful.
3,721 stars. Available on PyPI.
Use this if you need to quickly build a retrieval-augmented generation (RAG) system that uses a knowledge graph to improve the accuracy and relevance of answers to your questions over your own documents.
Not ideal if you need a pre-built, multi-user RAG solution with long-term memory for individual users without any coding.
Stars
3,721
Forks
399
Language
Python
License
MIT
Category
Last pushed
Jan 27, 2026
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/gusye1234/nano-graphrag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents