AI Potluck
Product / UX / Orchestration & agents

LightRAG

HKU Data Science Lab

Lightweight graph-based RAG framework from HKU Data Science Lab (EMNLP 2025) combining knowledge graphs with vector embeddings via dual-layer retrieval. Drops GraphRAG's expensive community-report step and supports incremental updates (add data without rebuilding the global index).

MIT. ~37k stars, ~251k monthly PyPI downloads (lightrag-hku).

Openness

5 high confidence
5.0
license
MIT(OSI)
source
public
core-gated
ungated

Fully MIT.

Adoption

4 medium confidence
4.0

~251k PyPI downloads/month (lightrag-hku) corroborating ~37k stars.

Capability

4 medium confidence
4.0

Deeper and more efficient than GraphRAG for graph-RAG; narrower than general orchestrators.

Unchanged since 2026-07-30 (last edited, not re-checked)