Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served through a standalone API server.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Graph Index
Use LightRAG to build an entity and relationship graph from raw documents: ‹what you need›
- Hybrid Query
Use LightRAG to combine vector similarity: ‹what you need›
- Incremental Update
Use LightRAG to add new documents to an existing index: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/HKUDS/LightRAG
Call the API
Auth None needed
Its page: github.com/HKUDS/LightRAG
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- None
- Skills
- 4
Skills
Graph Index
Builds an entity and relationship graph from raw documents to support multi-hop retrieval.
Hybrid Query
Combines vector similarity with graph traversal to retrieve context pure embedding search misses.
Incremental Update
Adds new documents to an existing index without rebuilding the whole knowledge graph.
API Serving
Serves retrieval over HTTP through a standalone server that agent harnesses can call directly.
