Agents

What is agent memory?

Agent memory is durable, queryable state an agent reads and writes across turns: messages, retrieved facts, and tool results, not a hidden JSON file.

Updated

How it works

  • Turns and artifacts are rows.
  • The next call reads the rows it needs.
  • You can query what the agent saw last week.

What it is not

It is not the model’s context window, and it is not a cache with no schema.

agent memory: this, and the thing it is confused with

agent memory: this, and the thing it is confused with
ThisNot this
LifetimeAcross processesUntil the prompt ends
ShapeTables you can queryA blob of messages
MediaCan sit on the same rowsText only, usually

Where Pixeltable fits

Pixeltable stores that memory as tables the agent reads with a query and writes with an insert.

Questions

How does agent memory work?
Turns and artifacts are rows. The next call reads the rows it needs. You can query what the agent saw last week.
What is agent memory often confused with?
It is not the model’s context window, and it is not a cache with no schema.