Glossary

What is agent memory?

Agent memory is how an AI agent retains information across turns or sessions — facts, past actions, user preferences — instead of starting blank each time. It ranges from short-term (the current context window) to long-term (a persistent store the agent recalls from when relevant).

In depth

Understanding agent memory

A model with no memory treats every request as the first. Memory fixes that: the agent can recall that you prefer a certain style, that it already tried an approach that failed, or that a project has a specific brand — so it builds on prior work instead of repeating it.

Short-term memory is whatever is in the context window right now. Long-term memory is a durable store — often a database or vector index — that the agent writes to and retrieves from, surfacing only the entries relevant to the current task (a context-engineering problem).

At the team level, memory blends into a company brain: shared, persistent knowledge every agent and person can draw on.

See it in Clearly

Company Brain

Persistent, shared knowledge your agents recall and act on.

The design workspace where these ideas are real

Agents that generate, a canvas they can see and drive, and a brain that keeps every asset on-brand. Free to start.