LightRAG
HKU Data Science LabLightweight graph-based RAG framework from HKU's Data Science Lab that combines a knowledge graph with vector embeddings through dual-level retrieval. It drops GraphRAG's expensive community-report step and supports incremental updates, so new data can be added without rebuilding the global index. It ships naive, local, global and hybrid query modes, pluggable storage, an API server and a web UI.
Openness
5 high confidence- license
- MIT(OSI)
- source
- public
- core features withheld
- no
Fully MIT: the repo publishes the full retrieval stack including the API server and web UI, with no hosted tier, enterprise directory or license key, so the core is ungated as well as OSI-licensed.
- https://github.com/HKUDS/LightRAG recorded 2026-08-13
MIT license, full public source including the API server and web UI, 38.8k stars and 5.5k forks; no hosted tier or enterprise directory
- https://raw.githubusercontent.com/HKUDS/LightRAG/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/HKUDS/LightRAG/main/README.md recorded 2026-09-29
The README documents the API server and admin console with "document management, knowledge-graph exploration, and query debugging"; searched the body for enterprise, license key and paid: none.
Adoption
3 medium confidenceAdoption is measured by PyPI downloads of lightrag-hku over the trailing month, corroborated by a large GitHub star count on the same repository.
- https://pypistats.org/api/packages/lightrag-hku/recent recorded 2026-08-12
313,096 downloads in the trailing 30 days for lightrag-hku
Capability
4 medium confidenceLightRAG builds a knowledge graph with dual-level retrieval, supports incremental updates and several query modes, and ships an API server and web UI. Its feature set is comparable to GraphRAG, while general-purpose orchestrators cover far more than graph RAG.
- https://github.com/HKUDS/LightRAG recorded 2026-08-13
dual-level retrieval, knowledge-graph construction, incremental updates, naive/local/global/hybrid query modes, pluggable storage, API server and web UI; no benchmark figure
- https://raw.githubusercontent.com/HKUDS/LightRAG/main/README.md recorded 2026-09-29
The README describes "dual-level retrieval mechanism" and lists "Incremental Updates & Selective Deletion", "Multiple Storage Backends", and query modes "hybrid", "naive" and "mix".
Verified 2026-09-24