Properties
| Name | Type | Description |
|---|---|---|
| subject | string | |
| predicate | string | |
| object | string | |
| user_id | object | End user this fact is about. One of user_id and agent_id is required: with neither (or only ids made of spaces, format characters or marks) the write is a 422 `identity_required`; run_id alone is not |
| agent_id | object | Agent namespace: the agent writing. One of user_id and agent_id is required: with neither (or only ids made of spaces, format characters or marks) the write is a 422 `identity_required`; run_id alone |
| run_id | object | |
| subject_type | string | What the subject is: any type of up to 20 characters, stored as sent on a new fact (an empty one as `unknown`). A write that restates a fact already true keeps the type the fact was first stored with, |
| object_is_literal | boolean | |
| confidence | number | |
| valid_from | object | |
| tense | string | current | past | planned. A past fact closes the open fact it restates. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/korely-ai/json-schema/korely-ai-fact-body-schema.json",
"title": "FactBody",
"x-generated": "2026-11-14",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/korely-ai-openapi.json#/components/schemas/FactBody",
"properties": {
"subject": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"title": "Subject"
},
"predicate": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"title": "Predicate"
},
"object": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"title": "Object"
},
"user_id": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "User Id",
"description": "End user this fact is about. One of user_id and agent_id is required: with neither (or only ids made of spaces, format characters or marks) the write is a 422 `identity_required`; run_id alone is not enough. 1 to 255 characters, no '/', no control character or other line break, and not '.' or '..': the id names a namespace that DELETE /v1/users/<user_id>/memories and DELETE /v1/agents/<agent_id> address as one URL path segment."
},
"agent_id": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Agent Id",
"description": "Agent namespace: the agent writing. One of user_id and agent_id is required: with neither (or only ids made of spaces, format characters or marks) the write is a 422 `identity_required`; run_id alone is not enough. 1 to 255 characters, no '/', no control character or other line break, and not '.' or '..': the id names a namespace that DELETE /v1/users/<user_id>/memories and DELETE /v1/agents/<agent_id> address as one URL path segment."
},
"run_id": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Run Id"
},
"subject_type": {
"type": "string",
"maxLength": 20,
"title": "Subject Type",
"description": "What the subject is: any type of up to 20 characters, stored as sent on a new fact (an empty one as `unknown`). A write that restates a fact already true keeps the type the fact was first stored with, and POST answers that fact's id. Extraction gives one of `concept`, `event`, `organization`, `person`, `place`, `product`, `unknown`. `self` (lower case, matched exactly): GET /v1/profile counts a fact so typed as one about the end user and lists it first, as it does a fact whose subject is the end user's id. The context block of GET /v1/context does not read the type: it tells the end user by the subject.",
"default": "unknown"
},
"object_is_literal": {
"type": "boolean",
"title": "Object Is Literal",
"default": false
},
"confidence": {
"type": "number",
"maximum": 1.0,
"minimum": 0.0,
"title": "Confidence",
"default": 0.9
},
"valid_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Valid From"
},
"tense": {
"type": "string",
"enum": [
"current",
"past",
"planned"
],
"title": "Tense",
"description": "current | past | planned. A past fact closes the open fact it restates.",
"default": "current"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"subject",
"predicate",
"object"
]
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/korely-ai-fact-body"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.