How ready are your agents for a bad day? Get your score

Persistent volumes

Disks that outlive the workload, for working memory and durable state.

WhereConsoleTerraform

Introduced Aug 5, 2026

run #1 writes /memoryworkload stopsrun #2 reads /memory
the volume survives · the workload does not

How it works

The workload is disposable. The volume is not.

Containers come and go; the disk under them stays.

Memory between runs.

Agents keep working state on volumes that survive between runs, and sandboxes keep their workspaces the same way.

Persistence is configuration.

State lives exactly as long as the disk under it — by decision, not by accident.

See it on your own cluster.

Thirty minutes, your infrastructure, your stack. Or skip the call — it is one Helm release onto a cluster you already run.