Mnemoverse · Schema
ReadResponseSchema
Response from a memory read query.
CompanyArtificial IntelligenceMemoryPersistent
Properties
| Name | Type | Description |
|---|---|---|
| items | array | List of matching memory items, ordered by relevance. |
| episodic_hit | boolean | True if an exact episodic (fingerprint) match was found. |
| query_concepts | array | Concepts extracted or used for the query. |
| expanded_concepts | array | Concepts expanded via concept associations. |
| search_time_ms | number | Search duration in milliseconds. |
| timings | object | Per-phase wall times in ms + call counters. Present only when the request set include_timings=true; an absent phase key means the phase was skipped. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/mnemoverse-com/json-schema/mnemoverse-com-read-response-schema-schema.json",
"title": "ReadResponseSchema",
"description": "Response from a memory read query.",
"x-generated": "2026-11-10",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/mnemoverse-com-memory-v1-api-openapi.yml#/components/schemas/ReadResponseSchema",
"properties": {
"items": {
"items": {
"$ref": "#/$defs/MemoryItemSchema"
},
"type": "array",
"title": "Items",
"description": "List of matching memory items, ordered by relevance."
},
"episodic_hit": {
"type": "boolean",
"title": "Episodic Hit",
"description": "True if an exact episodic (fingerprint) match was found."
},
"query_concepts": {
"items": {
"type": "string"
},
"type": "array",
"title": "Query Concepts",
"description": "Concepts extracted or used for the query."
},
"expanded_concepts": {
"items": {
"type": "string"
},
"type": "array",
"title": "Expanded Concepts",
"description": "Concepts expanded via concept associations."
},
"search_time_ms": {
"type": "number",
"title": "Search Time Ms",
"description": "Search duration in milliseconds."
},
"timings": {
"anyOf": [
{
"additionalProperties": {
"anyOf": [
{
"type": "number"
},
{
"type": "integer"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"title": "Timings",
"description": "Per-phase wall times in ms + call counters. Present only when the request set include_timings=true; an absent phase key means the phase was skipped."
}
},
"type": "object",
"required": [
"items",
"episodic_hit",
"query_concepts",
"expanded_concepts",
"search_time_ms"
],
"$defs": {
"MemoryItemSchema": {
"properties": {
"atom_id": {
"type": "string",
"format": "uuid",
"title": "Atom Id",
"description": "Unique identifier of the atom."
},
"content": {
"type": "string",
"title": "Content",
"description": "Stored text content of the memory."
},
"relevance": {
"type": "number",
"title": "Relevance",
"description": "Final relevance score, after outcome feedback (valence) is applied."
},
"similarity": {
"type": "number",
"title": "Similarity",
"description": "Raw cosine similarity between the query and the atom."
},
"valence": {
"type": "number",
"title": "Valence",
"description": "Outcome polarity [-1, +1]: positive = successful, negative = failed."
},
"importance": {
"type": "number",
"title": "Importance",
"description": "Importance score in [0, 1], computed at write time."
},
"source": {
"type": "string",
"title": "Source",
"description": "Retrieval stage that found this item. Production reads return semantic, concept_scoped (found under a concept extracted from the query) and hebbian_retrieval (missed by the direct stages and reached through learned associations, via a concept the query did not name); episodic marks an exact fingerprint match. Other stage names can appear: treat an unknown value as one more stage."
},
"concepts": {
"items": {
"type": "string"
},
"type": "array",
"title": "Concepts",
"description": "Concepts associated with this atom."
},
"domain": {
"type": "string",
"title": "Domain",
"description": "Domain/namespace of the atom."
},
"metadata": {
"additionalProperties": true,
"type": "object",
"title": "Metadata",
"description": "Arbitrary key-value metadata."
},
"provenance": {
"anyOf": [
{
"$ref": "#/$defs/ProvenanceSchema"
},
{
"type": "null"
}
],
"description": "Server-stamped authorship. Present only when the atom has recorded authorship; OMITTED entirely for legacy/unauthored atoms (mirrors the timings-omission pattern), so the default payload is unchanged for existing clients."
},
"created_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Created At",
"description": "UTC creation instant of the atom, ISO-8601. OMITTED for legacy atoms that predate timestamping — same omission pattern as `provenance`, so their payload shape is unchanged."
},
"occurred_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Occurred At",
"description": "When the remembered thing happened, as the write stated it (UTC, ISO-8601). OMITTED when the write gave none, so the item's time is then its `created_at`; same omission pattern as `provenance`."
},
"supersedes": {
"items": {
"type": "string",
"format": "uuid"
},
"type": "array",
"title": "Supersedes",
"description": "Ids of the revisions this item replaced. OMITTED when this item replaced nothing."
},
"superseded_by": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "null"
}
],
"title": "Superseded By",
"description": "Id of the revision that replaced this one. OMITTED while this item is the live tip. Present means the item is history — reported as a fact of the data regardless of server settings: while the read-side supersession filter is off, ordinary reads still return replaced revisions and this field is how you tell. Once the filter is on, history reaches a read only via `include_history`. The id names the IMMEDIATE successor as of the moment of replacement and carries no FK — if that successor was later destroyed, a GET on it is a documented 404, and `GET /memory/atoms/{id}/chain` reports the break rather than failing."
}
},
"type": "object",
"required": [
"atom_id",
"content",
"relevance",
"similarity",
"valence",
"importance",
"source",
"concepts",
"domain"
],
"title": "MemoryItemSchema",
"description": "Single memory item returned from a read query."
},
"ProvenanceSchema": {
"properties": {
"principal": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Principal",
"description": "The person/principal who wrote it."
},
"agent": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Agent",
"description": "Stable agent identifier, if any."
},
"agent_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Agent Name",
"description": "Human-readable agent name, if any."
},
"client_env": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Client Env",
"description": "Calling client environment: cursor·claude·chatgpt·chat·api·unknown."
},
"is_external": {
"type": "boolean",
"title": "Is External",
"description": "True when the principal is external to the org.",
"default": false
}
},
"type": "object",
"title": "ProvenanceSchema",
"description": "Server-stamped authorship of an atom.\n\nReturned (as the optional `provenance` object on a read item) only when at\nleast one field is non-null; an atom with no recorded authorship omits the\nwhole object. Stamped from VERIFIED JWT claims at write time — never\nclient-supplied."
}
}
}
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/mnemoverse-com-read-response-schema"
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.