LightRAG
Indexes your documents into a knowledge graph and answers agent questions with local, global, hybrid, or mix retrieval modes.
What it provides
Connect an existing HTTPS deployment, with a scoped token where the service requires one. Heavy jobs stay on that service instead of using bot memory.
Connection requirements
A LightRAG API server (default port 9621) published through HTTPS. Start it with LIGHTRAG_API_KEY set, keep X-API-Key selected, and paste the same key below. Send either X-API-Key or an account bearer token, never both: LightRAG validates the bearer token first and rejects the request if that one is invalid. Indexing, embeddings, and the graph store stay on the LightRAG host.
- Protocol
- REST / OpenAPI
- Endpoint
https://lightrag.example.com- Authentication
- x-api-key
post /query {"query":"What did we decide about pricing?","mode":"mix"}post /documents/text {"text":"Pricing was set at 20 USD per month."}Where to add it
Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.