GraphRAG
Graph-based retrieval-augmented generation system
GraphRAG is a research project from Microsoft that uses LLM-generated knowledge graphs to improve retrieval-augmented generation over private datasets. It can be run locally to index documents and answer complex queries.
Key features
- LLM-generated knowledge graphs
- Global and local query modes
- Community summarization
- Works on private data
Strengths
- Released under the MIT license
- Mature project with 35.3k GitHub stars
- Written in Python
GraphRAG replaces
Compare GraphRAG
16 head-to-head comparisons.
- GraphRAG vs OpenClaw
- GraphRAG vs Hermes Agent
- GraphRAG vs OpenCode
- GraphRAG vs Hugging Face Transformers
- GraphRAG vs Langflow
- GraphRAG vs Dify
- GraphRAG vs PaddleOCR
- GraphRAG vs RAGFlow
- GraphRAG vs OpenHands
- GraphRAG vs screenshot-to-code
- GraphRAG vs LightRAG
- GraphRAG vs Letta
- GraphRAG vs LLMWare
- GraphRAG vs R2R
- GraphRAG vs RAGApp
- GraphRAG vs Cheshire Cat AI
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