Skip to main content
An Actor represents a participant identity in MemoryLake. Every message in a conversation is attributed to an actor, and every fact extracted from those conversations is associated with one. Actors are the subject of memory — they are what MemoryLake “remembers about.”

​
Actor Types

The Actor API works with the people using your application. An actor you create here is a person — there is nothing else to choose. An agent is not reachable through this API. Agents have memories of their own, but you address them through the Agent endpoints, using the agent’s id. Nothing belonging to an agent is returned here, and an id that is not an actor’s answers 404.
If you previously read an agent’s memories through its identity actor, switch to the agent id. It is the same memories, named the way everything else names them.

​
How Actors Work

  1. Create an actor globally with a custom_id that maps to your user ID
  2. Bind the actor to one or more workspaces
  3. Use the actor’s ID when appending messages to conversations
  4. Query the actor’s accumulated facts via Actor Facts

​
An actor’s facts

An actor accumulates facts across every project in a workspace — “Jane prefers dark mode” — and they follow the actor from project to project. That is what gives each person a memory of their own throughout your application. Read them at:
Facts scoped to a project rather than to a person stay with the project. For how the scopes relate, see Memories.

​
Endpoints