Create Conversation - MemoryLake AI

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/workspaces/ws_abc123def456/memories/conversations' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "custom_id": "session-20250601-042",
    "name": "Product Feedback Call",
    "kind": "DIRECT",
    "rw_project_ids": ["proj_def456"],
    "metadata": {
      "channel": "zoom",
      "language": "en"
    },
    "actor_ids": ["actor_user_jane", "actor_assistant_v2"]
  }'

{
  "success": true,
  "data": {
    "id": "conv_7d2e3f4a5b6c7d8e",
    "name": "Product Feedback Call",
    "kind": "DIRECT",
    "metadata": {
      "channel": "zoom",
      "language": "en"
    },
    "custom_id": "session-20250601-042",
    "rw_project_ids": ["proj_def456"],
    "actor_ids": ["actor_user_jane", "actor_assistant_v2"],
    "current_message_id": null,
    "created_at": "2025-06-01T14:00:00Z",
    "updated_at": "2025-06-01T14:00:00Z"
  }
}

POST /openapi/memorylake/api/v3/workspaces/{workspaceId}/memories/conversations

Creates a new conversation within a workspace. A conversation groups related messages together so MemoryLake can extract structured facts from the exchange. You must attach exactly one read-write project via rw_project_ids — this is the project where extracted facts and memory are stored.

Permission required: workspace:conv_create (plus project:mem_add and project:doc_add on the specified project)

Path Parameters

string

required

Workspace identifier

Request Body

string

required

Caller-defined unique identifier. Use this to correlate the conversation with records in your own system.

string

required

Conversation kind: DIRECT (one-on-one) or GROUP (multi-participant).

array

required

Read-write project(s) the conversation reads context from and writes facts to. Exactly one project ID is required.

string

Display name for the conversation

object

Arbitrary key-value metadata to attach to the conversation

array

IDs of actors participating in the conversation. Each ID should reference an actor you have previously created.

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/workspaces/ws_abc123def456/memories/conversations' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "custom_id": "session-20250601-042",
    "name": "Product Feedback Call",
    "kind": "DIRECT",
    "rw_project_ids": ["proj_def456"],
    "metadata": {
      "channel": "zoom",
      "language": "en"
    },
    "actor_ids": ["actor_user_jane", "actor_assistant_v2"]
  }'

Response

object

Show Conversation object

string

Unique conversation identifier

string

Display name for the conversation

string

Conversation kind: DIRECT or GROUP

object

Arbitrary key-value metadata attached to the conversation

string

Caller-defined unique identifier

array

Read-write project(s) this conversation reads/writes memory to

array

IDs of actors participating in the conversation

string

ID of the latest message in the conversation

string

Creation timestamp

string

Last update timestamp

{
  "success": true,
  "data": {
    "id": "conv_7d2e3f4a5b6c7d8e",
    "name": "Product Feedback Call",
    "kind": "DIRECT",
    "metadata": {
      "channel": "zoom",
      "language": "en"
    },
    "custom_id": "session-20250601-042",
    "rw_project_ids": ["proj_def456"],
    "actor_ids": ["actor_user_jane", "actor_assistant_v2"],
    "current_message_id": null,
    "created_at": "2025-06-01T14:00:00Z",
    "updated_at": "2025-06-01T14:00:00Z"
  }
}

​Path Parameters

​Request Body

​Response

Path Parameters

Request Body

Response