Operator setup, console and restore-proven backups

The idea

A proven platform operator stores vendor apps and keys in the product. Values are sealed and the environment wins. The operator sees every org without SQL, and a weekly job proves the newest backup restores.

The problem
Setup needed SSH and .env edits, and a backup that was never restored proves nothing.
Why it matters
A key takes effect after a free vendor check and has a one-step revert, and backup health is visible.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

  • Redaction on write and the credential vault

    Secret-shaped values are removed before events, steps, tool results and model context are stored, and customer credentials are sealed with AES-256-GCM bound to org and credential.

  • Health components and incident watch

    Each module registers its own health checks, and /_health never calls a paid provider. A required component that fails past a grace period is filed once as an incident.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.