Core memory operations

Get a memory

Fetch one memory by id, including all typed facts currently extracted from it.

GET /v1/memories/{memory_id}

SDK: korely.get(memory_id). Returns the stored memory plus the facts currently active for it, the typed, bi-temporal triples Korely extracted server-side. Use it to inspect a single memory and the knowledge derived from it.

Authentication

HTTP header, required: Authorization: Bearer kor_live_....

Path parameter

This endpoint takes a single path parameter and no query parameters or request body.

Parameter	Type	Required	Description
`memory_id`	string	Required	The memory id from the URL path. Accepts a `mem_`-prefixed public id (e.g. `mem_8f2c1a`) or a bare UUID.

Example request

curl https://api.korely.ai/v1/memories/mem_8f2c1a \
  -H "Authorization: Bearer kor_live_..."

from korely_memory import Korely

korely = Korely(api_key="kor_live_...", region="eu")

memory = korely.get("mem_8f2c1a")

print(memory.content)        # "Giulia prefers async standups and works in CET."
print(len(memory.facts))     # 1

import { Korely } from "korely-memory";

const korely = new Korely({ apiKey: "kor_live_..." });

const memory = await korely.get("mem_8f2c1a");

console.log(memory.content);     // "Giulia prefers async standups and works in CET."
console.log(memory.facts.length); // 1

Response

200 OK. The memory, plus every typed fact currently active for it.

{
  "id": "mem_8f2c1a",
  "content": "Giulia prefers async standups and works in CET.",
  "user_id": "customer-giulia-4812",
  "agent_id": "onboarding-bot",
  "run_id": null,
  "metadata": {"source": "slack"},
  "created_at": "2026-03-01T09:14:22+00:00",
  "updated_at": "2026-03-01T09:14:22+00:00",
  "facts": [
    {
      "id": "fct_a1",
      "subject": "Giulia",
      "subject_type": "person",
      "predicate": "prefers",
      "predicate_raw": "prefers",
      "object": "async standups",
      "object_is_literal": true,
      "predicate_family": "preference",
      "confidence": 0.91,
      "user_id": "customer-giulia-4812",
      "agent_id": "onboarding-bot",
      "valid_from": "2026-03-01T00:00:00+00:00",
      "invalid_at": null,
      "invalidated_by": null,
      "source_memory_id": "mem_8f2c1a",
      "created_at": "2026-03-01T09:14:25+00:00"
    }
  ]
}

Field	Type	Description
`id`	string	Public memory id (`mem_` prefixed).
`content`	string	Memory content.
`user_id`	string · null	End user this memory belongs to (engine `end_user_id`), nullable.
`agent_id`	string · null	Agent namespace, nullable.
`run_id`	string · null	Run sub-namespace, nullable.
`metadata`	object	Developer metadata dict.
`created_at`	string · null	ISO 8601 timestamp, nullable.
`updated_at`	string · null	ISO 8601 timestamp, nullable.
`facts`	array<object>	Facts currently extracted from this memory. Each fact carries `id` (`fct_` prefixed), `subject`, `subject_type`, `predicate`, `predicate_raw`, `object`, `object_is_literal`, `predicate_family`, `confidence`, `user_id`, `agent_id`, `valid_from`, `invalid_at`, `invalidated_by`, `source_memory_id`, and `created_at`.

Errors

Status	Code	Cause
`401`	`invalid_key`	Missing or invalid `kor_live_` key, `Invalid or missing API key`.
`403`	`forbidden`	The key lacks the `memories:read` scope.
`404`	`not_found`	Unparseable memory id, or no memory matches that id, `Memory not found`.
`429`	`quota_exceeded`	Monthly query quota exceeded.
`429`	`rate_limit_exceeded`	Rate limit exceeded. Honor the `Retry-After` header.

Notes

Accepts both id forms. Pass a mem_-prefixed public id or a bare UUID, both resolve to the same memory.
Facts are the active set. The facts array holds the currently active facts for this memory. Superseded facts are not returned here.
Counts as one read. Each get counts against your monthly query quota. The read is logged before the existence check, so a 404 still counts.

Search memories, find memories by semantic query.
Get context, the assembled recall block, facts plus memories.
SDK reference, the typed client methods.