WeKnora
Search indexed documents in your WeKnora knowledge bases and return matching source passages. Requires an existing WeKnora deployment outside the bot, an HTTPS endpoint, and a workspace API key scoped to the knowledge bases you want to search.
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
Run WeKnora outside the bot with its database, document parser, and embedding model configured. Enter the HTTPS server origin without an /api/v1 suffix. Have the workspace owner create a scoped workspace API key with full_access=false, capabilities=["retrieve"], and a non-empty knowledge_base_ids allow-list; keep X-API-Key selected and paste that key below. The examples list accessible knowledge bases and search indexed documents as JSON; replace KNOWLEDGE_BASE_ID with an allowed ID. Chat endpoints use SSE and are not part of these retrieval examples. Search may return resource:// handles that this connector cannot download directly. WeKnora is MIT-licensed; bundled third-party components retain their own licenses.
- Protocol
- REST / OpenAPI
- Endpoint
https://weknora.example.com- Authentication
- x-api-key
get /api/v1/knowledge-basespost /api/v1/knowledge-search '{"query":"How do I reset my password?","knowledge_base_ids":["KNOWLEDGE_BASE_ID"]}'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.