Five named components.
Each with one guarantee.

What it learns, it keeps. Across every session, every restart, every model swap. There is no "start over" mode because there is no "forgot you" mode.

What it learned yesterday answers your question this morning.

You will set a goal and they will pick it up: cheap models when cheap is enough, smart ones when smart is necessary, asleep when there is nothing to do. When they sleep, you pay nothing.

Set a goal at midnight, wake up to the work done. No paid context window ticking while it waits.

Every request goes to the cheapest brain that can answer it correctly. You don't pay for genius when reflex will do. You don't get a reflex answer to a question that needs depth.

Cheap models for cheap work. Smart ones when they matter.

And when a provider says you are over your limit →

Your keys, tokens, secrets are sealed by your operator key. The model receives outcomes, what an API returned, never the credential itself. Even we cannot read what you've sealed.

A prompt that asks for your keys gets nothing. They were never readable

The mind will live in its own machine on your laptop: signed at boot, isolated from your host, with a kill switch you control. We do not have a back door, and there will be nothing to phone home.

Arrives as an update. You pull the plug; it can't escape.