API

The memo.st API stores durable facts that agents can retrieve across sessions. The API worker lives in apps/api, runs on Cloudflare Workers, and exposes JSON endpoints under /v1/memories.

Memory model

Every memory is scoped by four caller-provided fields:

• organizationId isolates tenant data.
• subjectId identifies the user, account, project, or entity the fact is about.
• agentId records which agent created or owns the memory.
• namespace separates use cases such as support, sales, or research.

Base routes

GET  /health
GET  /v1/memories
POST /v1/memories
GET  /v1/memories/:id
POST /v1/memories/search

First memory

{
  "organizationId": "org_demo",
  "subjectId": "customer_acme",
  "agentId": "support-agent",
  "namespace": "support",
  "content": "Acme prefers Slack escalation for P0 incidents."
}

Add an embedding array when the caller already generated a vector. Without an embedding, the API stores the memory in D1 and skips Vectorize indexing for that request.