The operating system for people running real AI agents.
FleetCrown is built for operators already running multiple AI agents across multiple projects. It makes the work visible, steerable, and recoverable.
One conversational composer turns plain language into action — “code review for kivvi” dispatches it into that project; a question gets answered. The system picks the project and the path, so you hold less in your head.
Every project, active agent, queue item, and handoff sits in one operating view instead of disappearing into terminal tabs.
The local runner owns the agent terminals, git, agent launching, and handoff files. FleetCrown coordinates the work without turning your environment into a cloud sandbox.
Fleet-wide play/pause with per-project queues and overrides — each project asks for oversight only when the next decision actually needs you.
Real reports from the feedback widget, fixed by the fleet and deployed — 32 resolved so far.
“On mobile (320px wide), the feedback widget's floating action button (fixed, 48x48px, z-index 2147483000, bottom-right corner) permanently o…”
Most tools help you write code faster in one file or one project. FleetCrown is for running real agent operations at fleet scale — choose your entry point.
Install or build the Fleet Runner, connect an agent token, and let your real machine become the authoritative execution surface.
Download runner →Create an account, add projects, and command agent sessions from the hosted web surface.
Start building →Understand the local-runner, remote-control, queue, and handoff design before committing your workflow to it.
View whitepaper →