Nebula stores what your agents learn and lets them retrieve it by meaning. Store text and conversations into a collection, then search that collection and get back answers with citations.

curl -X POST "https://api.zeroset.com/v2/collections/018f3c2a-6b41-7d8e-9a52-4c1e77b0d3aa/memories/search" \
  -H "Authorization: Bearer $NEBULA_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "what did we decide about exports", "retrieval_id": "018f3c2a-8d55-7a21-88bf-6e0d43c9a115"}'

Start here

• Quickstart — first memory stored and searched.
• Concepts — resource hierarchy and compact URLs.
• Authentication — how keys are scoped.

Build

Workspaces · Collections · Memories · Search · Operations · Metadata

Integrate

TypeScript and Python clients, and a MCP integration overview for agents that speak Model Context Protocol.