Building the operating system for people running serious AI agent operations — and for the robotic fleets that come next.
Live in production. The system already coordinates real fleets across real projects.
The web control plane coordinates fleets of AI agents across projects, with one-button autopilot: pause all, or build all.
One local execution path: the desktop app owns the agent terminals, agent launching, and state sync — the same React tree the web serves.
Concrete engineering, in sequence: distribution first, then the remote control channel, then mobile on top of it.
Make Fleet Runner trivial to install and keep current on every platform — including for builders who never open a terminal.
Web and mobile become genuine remote control surfaces — not eventually-consistent dashboards.
Native iOS and Android apps on the remote control channel — optimized for steering and approval, not authoring.
Directions we are committed to that are design and strategy work today. Nothing here is presented as available.
When the local machine is unavailable, parallel cloud agents take over — with explicit handoff, never as the default.
The same evidence that decides whether a run was done should decide how the next one is briefed — with a human gate on every learned change.
Same control plane, multiple operators, multiple machines — shared fleet views, per-operator permissions, per-project autonomy ceilings.
Build independently in FleetCrown. Optionally link an OrangeCat profile for public updates and funding, with separate consent before publishing work.
Track each project's surrounding relationships — competitors, collaborators, investors, customers — as typed edges in OrangeCat's entity graph, surfaced on FleetCrown for the agent to act on. Competitors ship first as the most automatable category.
Read the essay: Where Stakeholders Live →Make it natural to fund what people build and build what people choose to fund, without pretending the full loop is already automated.
The same control patterns — autonomy dial, handoff, queues, visibility, override — applied to a different execution substrate. Not a separate product line bolted on later.
These do not change as the phases ship. They are constraints we hold across every stage.
When the user's machine can do the work, it should. We do not push everyone into remote sandboxes.
Frontier subscriptions are often the best tool. But the infrastructure does not require them — the user points their fleet at whatever model serves their goals best.
Pause all, or build all — with per-project overrides. Per project. Per moment. Never forced.
The local client connects out to the control plane, not the other way around. Easier to firewall. Easier to reason about. Credible to security-conscious operators.
Every agent's state is legible. No black boxes inside your own fleet.