Why a team, not one more chat.
The single AI chat is a bottleneck: serial work, bot-authored commits, and "it ran somewhere I can't see or review." We think the unit of AI coding should be a team you design — not a box you babysit.
- Mira Architect
- Otis Reviewer
- Juno Frontend
- Kit QA Automation
- Remy DevOps
- Sol API Designer
So Uai runs a crew of agents that plan, build, review each other, and open PRs as you — many tasks at once, each sandboxed on the runner you choose, with your keys and your name on the work. The cloud orchestrates. Self-hosted runners are secret-blind by design; Uai Cloud runners aren't, and we say so plainly.
A fuller story is on the way. In the meantime, the product is the argument: see how it works.
See the argument in code.
The clearest way to get it is to run one task. Design a crew and point it at your repo.