Glossary · long-running-agent

Long-running agent

Definition

An AI coding agent that operates for hours or days without continuous human supervision. Long-running agents survive lid closes, network changes, and laptop reboots because they live on a persistent server. They check in for approval on privileged actions and continue otherwise. The human reviews progress at their own cadence rather than babysitting every step.

Context

On a laptop, an agent's session ends when the laptop sleeps; long-running work has to fit inside the time the user is at the keyboard. On a persistent agent workstation, the same agent keeps making progress through overnight refactors, multi-day migrations, and end-to-end test suites that take eight hours to run. Recovery from crashes is automatic. Supervisor processes restart the agent and resume from the last checkpoint, so a single bad call doesn't lose a night's work.

Also known as

always-on agentovernight agentunattended agentbackground agent

Related terms

See also