Skip to main content
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

workspaceId
string
required
Workspace identifier

Request Body

custom_id
string
required
Caller-defined unique identifier. Use this to correlate the conversation with records in your own system.
kind
string
required
Conversation kind: DIRECT (one-on-one) or GROUP (multi-participant).
rw_project_ids
array
required
Read-write project(s) the conversation reads context from and writes facts to. Exactly one project ID is required.
name
string
Display name for the conversation
metadata
object
Arbitrary key-value metadata to attach to the conversation
actor_ids
array
IDs of actors participating in the conversation. Each ID should reference an actor you have previously created.

Response

data
object