GraphRAG

Microsoft’s MIT library for graph-based RAG over whole document corpora.

Install Repository Website Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 8 GB
Gpu: Not needed
Docker: No
Setup: Advanced
Deploy as: Local, Self-hosted
Commercial use: Allowed

Needs an LLM endpoint for indexing; local runners work with configuration.

Project.

Fetched Sep 12, 2026¹

License: MIT
Stars: 36k¹
Forks: 3.8k¹
Open issues: 11¹
Language: Python¹
Last commit: Sep 8, 2026¹
Tags: ragknowledge-graphmicrosoft

About.

GraphRAG is Microsoft’s answer to “the answer spans the whole corpus”: it extracts a knowledge graph from your documents and answers global questions via community summaries. Indexing is slow and needs a model endpoint. MIT.

knowledge graph extraction · community detection · global search · query focused summarization

Alternatives.

Nearby.

All RAG and app builders

LllamafileSingle-file LLM runtime from Mozilla. Download, chmod, run.Compare
LLiteLLMProxy that translates many model APIs into one OpenAI-shaped client.Compare
VvLLMHigh-throughput model server for GPU inference.Compare
FFlowiseLow-code node UI on top of LangChain-style flows.Compare
Lllama.cppC/C++ runtime that made local GGUF models practical.Compare