GraphRAG

license

MIT(OSI)

source

public

core features withheld

no

Fully MIT: the repo publishes the complete indexing and query pipeline and offers no hosted tier, enterprise directory or license key, so the core is ungated as well as OSI-licensed.

• https://github.com/microsoft/graphrag recorded 2026-08-13

  MIT license, full public source for the indexing and query pipeline, 35.5k stars and 3.7k forks; no hosted tier or enterprise directory

• https://raw.githubusercontent.com/microsoft/graphrag/main/LICENSE recorded 2026-09-29

  The LICENSE file is the standard MIT text: "MIT License" and "Permission is hereby granted, free of charge, to any person obtaining a copy" with no added restrictions.

• https://raw.githubusercontent.com/microsoft/graphrag/main/README.md recorded 2026-09-29

  The README describes the pipeline as "a data pipeline and transformation suite" and offers a "command line quickstart"; Searched the body for enterprise, license key and hosted: none.

PyPI downloads are the basis for this reading, since graphrag is the package's declared distribution channel. GitHub stars on the same repository move in the same direction and corroborate the reading rather than driving it.

• https://pypistats.org/api/packages/graphrag/recent recorded 2026-08-14

  last_month = 69,377 downloads for graphrag (last_week 13,302, last_day 2,016).

GraphRAG is turnkey for knowledge-graph-based retrieval: it extracts a graph, detects communities, generates summaries and supports Global, Local and DRIFT query modes with automatic prompt tuning. No benchmark exists for this kind of technique, so it is judged on feature depth, and it is deliberately narrower in scope than a general agent like OpenHands, placing it a step below.

• https://microsoft.github.io/graphrag/ recorded 2026-09-29

  The docs describe "extracting a knowledge graph out of raw text, building a community hierarchy, generating summaries for these communities" and list Global Search, Local Search, DRIFT Search and Prompt Tuning.