Agent Memory

Agent memory lets agents persist state across runs so they can continue work instead of starting from scratch each time.

When Agent Memory Is Critical

Agent memory is particularly critical in several scenarios:

• Long-running agents with multi-step executions.
• Flows where each step needs to save data for the next step.
• Cases where generated data is too large to keep only in runtime memory and must be persisted.
• Advanced orchestration patterns where one agent must pass a large amount of information to another agent.

How Agent Memory Works

By default, agent memory is recorded per squad, per agent, and per run.

Depending on the orchestration need, memory can also be limited to:

• Per squad and per agent.
• Per agent and per run.
• Per squad and per run.
• Per squad only.

With different scope limits, agent memory can behave like a common repository, a whiteboard for collaboration, or a run-specific handoff buffer.