Properties
| Name | Type | Description |
|---|---|---|
| id | string | |
| slug | string | Unique per person. What you put in the path (or `me`, for the agent a key is bound to). |
| name | string | |
| kind | string | `personal` works for the person; `product` works for other people (it keeps `user_id` memories). |
| purpose | stringnull | |
| avatar_url | stringnull | The picture the person gave this agent in their dashboard, or null (it then wears the mark of the tool it lives in, or its initial). Read only: no request sets it. |
| status | string | A paused agent keeps and recalls nothing (423). A retired one (the person retired it in their agents space) holds no key and answers the same, but can still be read and exported. |
| created_via | string | |
| created_at | string | |
| updated_at | string | |
| last_active_at | stringnull | |
| parent | stringnull | The slug of the agent this one works under, or null for a top-level agent. A sub-agent has a memory, keys and settings of its own (it started as a copy of its parent's); two levels only. An agent's ow |
| access | string | What it may do with the person, in one word (`asks` is "asks first"); `mix` when its settings are a mix of their own. |
| settings | object | |
| counts | object | On a list and a single read. What the agent keeps now (current versions, not expired). |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/innernet-live/json-schema/innernet-live-agent-schema.json",
"title": "Agent",
"x-generated": "2026-11-12",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/innernet-live-openapi.json#/components/schemas/Agent",
"type": "object",
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"slug": {
"type": "string",
"description": "Unique per person. What you put in the path (or `me`, for the agent a key is bound to)."
},
"name": {
"type": "string",
"maxLength": 80
},
"kind": {
"type": "string",
"enum": [
"personal",
"product"
],
"description": "`personal` works for the person; `product` works for other people (it keeps `user_id` memories)."
},
"purpose": {
"type": [
"string",
"null"
],
"maxLength": 280
},
"avatar_url": {
"type": [
"string",
"null"
],
"format": "uri",
"description": "The picture the person gave this agent in their dashboard, or null (it then wears the mark of the tool it lives in, or its initial). Read only: no request sets it."
},
"status": {
"type": "string",
"enum": [
"active",
"paused",
"retired"
],
"description": "A paused agent keeps and recalls nothing (423). A retired one (the person retired it in their agents space) holds no key and answers the same, but can still be read and exported."
},
"created_via": {
"type": "string",
"enum": [
"dashboard",
"api",
"connection"
]
},
"created_at": {
"type": "string",
"format": "date-time"
},
"updated_at": {
"type": "string",
"format": "date-time"
},
"last_active_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"parent": {
"type": [
"string",
"null"
],
"description": "The slug of the agent this one works under, or null for a top-level agent. A sub-agent has a memory, keys and settings of its own (it started as a copy of its parent's); two levels only. An agent's own key is never told its parent."
},
"access": {
"type": "string",
"enum": [
"sealed",
"asks",
"trusted",
"mix"
],
"description": "What it may do with the person, in one word (`asks` is \"asks first\"); `mix` when its settings are a mix of their own."
},
"settings": {
"$ref": "#/$defs/AgentPolicy"
},
"counts": {
"type": "object",
"description": "On a list and a single read. What the agent keeps now (current versions, not expired).",
"properties": {
"memories": {
"type": "integer"
},
"users": {
"type": "integer"
},
"about_you": {
"type": "object",
"properties": {
"held": {
"type": "integer"
},
"kept": {
"type": "integer"
},
"declined": {
"type": "integer"
},
"auto": {
"type": "integer"
}
}
}
}
}
},
"$defs": {
"AgentPolicy": {
"type": "object",
"description": "An agent's settings: one object, the same in the dashboard and here. Every setting has a default, a PATCH deep-merges into what is there (lists replace), and one wrong setting refuses the whole patch with a sentence naming it.",
"properties": {
"memory": {
"type": "object",
"description": "What it keeps.",
"properties": {
"infer": {
"type": "boolean",
"default": true,
"description": "Read what it is told into separate memories (one model call), or keep the text as given."
},
"instructions": {
"type": "string",
"maxLength": 4000,
"default": "",
"description": "What to keep, in your words."
},
"kinds": {
"type": "array",
"minItems": 1,
"items": {
"type": "string",
"enum": [
"fact",
"preference",
"episode",
"procedure",
"instruction",
"note"
]
},
"description": "The kinds it keeps; anything else is skipped. Default: all six."
},
"exclude": {
"type": "array",
"maxItems": 20,
"items": {
"type": "string",
"maxLength": 80
},
"description": "Topics it never keeps."
},
"redact": {
"type": "object",
"description": "Taken out BEFORE anything is stored or sent to a model.",
"properties": {
"emails": {
"type": "boolean",
"default": false
},
"phones": {
"type": "boolean",
"default": false
},
"secrets": {
"type": "boolean",
"default": true
},
"cards": {
"type": "boolean",
"default": true
}
}
},
"retention": {
"type": "object",
"description": "Days until a memory is deleted (null = never). `run_days` applies to anything with a run_id, `episode_days` to episodes.",
"properties": {
"default_days": {
"type": [
"integer",
"null"
],
"minimum": 1,
"maximum": 3650,
"default": null
},
"episode_days": {
"type": [
"integer",
"null"
],
"minimum": 1,
"maximum": 3650,
"default": 90
},
"run_days": {
"type": [
"integer",
"null"
],
"minimum": 1,
"maximum": 3650,
"default": 30
}
}
},
"max_memories": {
"type": "integer",
"minimum": 100,
"maximum": 100000,
"default": 10000,
"description": "Counts earlier versions too: earlier versions go first, then the oldest, least important memories."
},
"dedupe": {
"type": "string",
"enum": [
"merge",
"keep"
],
"default": "merge",
"description": "`merge` makes a near-duplicate the next version of the memory it repeats; `keep` keeps both."
}
}
},
"person": {
"type": "object",
"description": "What it learns about the person who owns it, and how much of them it may read.",
"properties": {
"funnel": {
"type": "string",
"enum": [
"off",
"ask",
"auto"
],
"default": "ask",
"description": "`ask` holds each one for the person's yes, `auto` files it at once, `off` keeps it with the agent."
},
"min_confidence": {
"type": "number",
"minimum": 0.5,
"maximum": 1,
"default": 0.7,
"description": "Below this, a memory is kept as the agent's own and never offered."
},
"never": {
"type": "array",
"items": {
"type": "string"
},
"description": "Personal dimensions it may never file under. Default: relationships, hauntings, kin, somatic."
},
"disclosure": {
"type": "string",
"enum": [
"private",
"self",
"trusted",
"work"
],
"default": "private",
"description": "The class floor for anything it files; the fold can only make it more private."
},
"read": {
"type": "string",
"enum": [
"none",
"standard",
"personal",
"private"
],
"default": "standard",
"description": "How deep into the person's own memory it may read when it recalls with include_person."
}
}
},
"recall": {
"type": "object",
"description": "How it remembers.",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 10
},
"threshold": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0
},
"rerank": {
"type": "boolean",
"default": false,
"description": "Re-read the best candidates by meaning (in-process embeddings, nothing stored)."
},
"recency": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.3,
"description": "How much newer beats older."
},
"include_person": {
"type": "boolean",
"default": false
}
}
},
"limits": {
"type": "object",
"properties": {
"writes_per_minute": {
"type": "integer",
"minimum": 1,
"maximum": 6000,
"default": 120
},
"reads_per_minute": {
"type": "integer",
"minimum": 1,
"maximum": 20000,
"default": 600
},
"extract_per_day": {
"type": "integer",
"minimum": 0,
"maximum": 100000,
"default": 1000,
"description": "0 turns reading off: a remember with `infer` on answers 400. All of one person's agents also share 20,000 a day."
}
}
}
}
}
}
}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/innernet-live-agent"
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. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.