openmemory
Docs
Memories

Remember from a conversation: get a job for your model

POST
/v1/memories/extract

Returns instructions, the related facts already stored, and an output schema. Run them with your own model, then submit its JSON to /v1/memories/extract/result. The server uses no model of its own for this and does not store the conversation.

Authorization

headerAuthorizationBearer <token>

Your space key (om_...). Create one with POST /v1/spaces.

Request Body

application/json
  1. body
messages?array<>

The conversation. Not stored. Omit it if your model already has the conversation; send about instead.

Items1 <= items <= 100
about?string

What the conversation is about, used to find related facts.

Lengthlength <= 500

Response Body

The job

application/json
  1. response
instructions*string
input*
output_schema*
max_facts*integer
Example Request
curl -X POST 'https://api.openmemory.sh/v1/memories/extract' \  -H 'Content-Type: application/json' \  -d '{}'
Example Response
{  "instructions": "string",  "input": {    "property1": null,    "property2": null  },  "output_schema": {    "property1": null,    "property2": null  },  "max_facts": 0}

Delete one fact DELETE

Previous Page

Remember from a conversation: submit your model's facts POST

Stores the facts in one transaction. A fact with `replaces` hides the older fact right away; the next dream removes it, and until then PATCH expires_at to null brings it back. Pinned facts are never replaced, and only a fact the person stated can replace another fact the person stated.