Claude Platform Docs

Criar um armazenamento de memória

POST/v1/memory_stores

Criar um armazenamento de memória

Headers
"anthropic-version": optional string

The version of the Claude API you want to use.

Read more about versioning and our version history here.

"anthropic-beta": optional array of AnthropicBeta

This endpoint is in beta: requests must send agent-memory-2026-07-22 or managed-agents-2026-04-01 in this header.

One of the following:
string
"message-batches-2024-09-24"
"prompt-caching-2024-07-31"
"computer-use-2024-10-22"
"computer-use-2025-01-24"
"pdfs-2024-09-25"
"token-counting-2024-11-01"
"token-efficient-tools-2025-02-19"
"output-128k-2025-02-19"
"files-api-2025-04-14"
"mcp-client-2025-04-04"
"mcp-client-2025-11-20"
"dev-full-thinking-2025-05-14"
"interleaved-thinking-2025-05-14"
"code-execution-2025-05-22"
"extended-cache-ttl-2025-04-11"
"context-1m-2025-08-07"
"context-management-2025-06-27"
"model-context-window-exceeded-2025-08-26"
"skills-2025-10-02"
"fast-mode-2026-02-01"
"output-300k-2026-03-24"
"user-profiles-2026-03-24"
"user-profiles-2026-08-18"
"user-profiles-2026-09-04"
"advisor-tool-2026-03-01"
"managed-agents-2026-04-01"
"cache-diagnosis-2026-04-07"
"dreaming-2026-04-21"
"thinking-token-count-2026-05-13"
"server-side-fallback-2026-06-01"
"server-side-fallback-2026-07-01"
"fallback-credit-2026-06-01"
"fallback-credit-2026-07-01"
"agent-memory-2026-07-22"
"mid-conversation-tool-changes-2026-07-01"
"compact-2026-01-12"
"computer-use-2025-11-24"
"mcp-tunnels-2026-06-22"
"structured-outputs-2025-11-13"
"task-budgets-2026-03-13"
"thinking-display-updates-2026-08-18"
"ce-user-management-2026-07-13"
"mid-conversation-output-config-2026-07-01"
"thinking-binding-controls-2026-08-01"
"mid-conversation-system-clear-at-2026-08-21"
"compact-2026-09-04"
"inline-tools-2026-09-15"
"mcp-client-2026-09-15"
"ce-plugins-2026-09-01"
"spend-limit-reads-2026-09-26"
"telemetry-destinations-2026-08-11"
"webhooks-2026-10-07"
"anthropic-workspace-id": optional string

Optional header to select the Workspace for this request. The value is a Workspace ID (for example, wrkspc_011CZkZaBF1tNoB5wlCeusgy).

Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.

Body
name: string

The name of the memory store, 1 to 255 characters long, without control characters. Names don't have to be unique in a workspace.

In a session, the store's directory under /mnt/memory/ is based on this name. The name is lowercased and every run of characters other than ASCII letters and digits becomes one hyphen. The session's memory store resource gives the exact path in mount_path.

See the memory guide to learn more about how agents access memory stores.

minLength1
maxLength255
description: optional string

Free-text description of what the store contains, up to 1,024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent.

maxLength1024
metadata: optional map[string]

Key-value pairs for your own use, such as the end user that the store belongs to. The agent doesn't see them.

A store has at most 16 pairs. Keys are 1 to 64 characters long and values at most 512 characters.

Returns
BetaManagedAgentsMemoryStore object{ type: "memory_store", id, archived_at, 5 more }

A memory_store: a named container for agent memories, scoped to a workspace. Attach a store to a session via resources[] to mount it as a directory the agent can read and write.

type: "memory_store"
id: string

The unique ID of the memory store (memstore_...). Use it to attach the store to a session.

archived_at: string or null

When the memory store was archived, in RFC 3339, or null if it hasn't been.

Archiving can't be undone. An archived store can't be attached to new sessions. You can't create or update its memories or update the store. You can still read and delete its memories, redact their versions, and delete the store.

See the memory guide to learn more about archiving.

formatdate-time
created_at: string

When the memory store was created, in RFC 3339.

formatdate-time
description: string

Free-text description of what the store contains, up to 1,024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. Empty string when unset.

metadata: map[string]

Key-value pairs for your own use, such as the end user that the store belongs to.

A store has at most 16 pairs. Keys are 1 to 64 characters long and values at most 512 characters. You can't filter lists by metadata.

name: string

Human-readable name for the store. 1–255 characters. The store's mount-path slug under /mnt/memory/ is derived from this name.

updated_at: string

When the memory store was last changed, in RFC 3339.

Changing its name, description, or metadata updates it. Archiving the store does too. Changes to the store's memories don't.

formatdate-time
Criar um armazenamento de memória
curl https://api.anthropic.com/v1/memory_stores \
    -H 'Content-Type: application/json' \
    -H 'anthropic-version: 2023-06-01' \
    -H 'anthropic-beta: agent-memory-2026-07-22' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY" \
    -d '{
          "name": "x"
        }'
Returns Examples
Response 200
{
  "id": "id",
  "archived_at": "2019-12-27T18:11:19.117Z",
  "created_at": "2019-12-27T18:11:19.117Z",
  "description": "description",
  "metadata": {
    "foo": "string"
  },
  "name": "name",
  "type": "memory_store",
  "updated_at": "2019-12-27T18:11:19.117Z"
}