More than thirty providers plus fully local inference. You bring your own keys and pay the provider directly. There is no markup, no per-seat fee, and no meter between you and the model.
Different roles in a piece of work, planning, editing, mechanical search, review, are routed to the model you configured for each, chosen with a vendor-neutral recommender based on measured reliability rather than a house preference.
What that gets you. You are not paying frontier prices for mechanical work, and the routing is yours to override.
Slow batch work, like describing memories and summarising documents, runs on this machine by default, or on a larger one you trust if you set that up. Interactive chat always stays local.
What that gets you. A laptop does not have to do everything, without your conversation leaving it.
Everything on this page describes behaviour that ships today. The facts come from the runtime’s own capability brief, the same one the agent reads about itself on every turn, so nothing here is a roadmap item wearing a present tense.
How does an AI agent remember across sessions?
Can an AI agent run without sending your data to the cloud?
Can an AI agent work while you sleep?
What can an AI agent actually do on your computer?
How do you stay in control of an autonomous agent?
What stops an AI agent from going off the rails?