Specialized capacity, when you need it, composed by you, paid according to use.
Delivered through toast, composable AI for the command line.
There is no framework or harness to learn. Unix solved how people and programs work together fifty years ago, and it works for AI too.
Slices: toast reviewer, toast editor, toast kimi. A name for a job or a mind, with the model behind it chosen and tested by us and replaced when a better one appears.
One call, a pipe, a loop, or a cron line. Nothing runs until something asks, and you decide how much the machine does before you read the result.
You write the pipeline in the shell you already use. A file lists what the model may run; every command is printed before it runs; every change can be undone.
Local models and your own keys cost nothing. Our models are metered by the token, on one balance. Pro, the toolkit, is its own package.
Apple's on-device model is free and shows you how the tools work. Credits pay for our models and the slices. Pro is the toolkit: loops, undo, schedules, messaging, a local 30B model.
toast reviewer, toast editor, toast kimi — the slicesAt every step, three things hold: a file in your directory lists the commands the model may run; every command is printed before it runs; and every change is recorded with a reason and can be undone.
Chat makes you work. Agents do too much. With toast you select the level of delegation required by the task, with one or more specialized models working for you, alone or together.
$ log stream | head -200 | toast "narrate like a nature documentary" | say Here, in the quiet of a Saturday afternoon, the launch daemon stirs. It has noticed the Wi-Fi. It does not approve. $ arp -an | toast "introduce each device like you are in a bar" .1 is the router. Runs the place. Doesn't drink. .4 is "Toaster". Small, but persistent. And .2 and .6? Strangers.
The tutorial, with every command → Steps 4 to 6 need Pro.
What is Unix? Press ` to open a Unix terminal. To close, press ` again. Type help to start.
