The studio runs about twenty local test servers, one or more per game, site, bot and agent tool. Until now nobody could see them all at once. Each project started its own, and some ran for days after the session that started them had ended.
Control Room is one page, opened from a desktop icon, that lists every registered server: running or stopped, how long it's been up, its memory and CPU, and what will stop it (Control Room itself, the Claude app, a window the owner opened, or nothing at all, which makes it an orphan). Each row can be started, stopped or restarted. Start all brings up every main server that isn't already running, then offers to open them all in the browser.
It keeps no list of its own. It reads the studio's port registry and each project's start command live, so a newly registered server appears on the next refresh.
It flags problems: two servers on one port, a server on a port nobody registered, a one-off tool still listening, a server reachable from the network, and a server it has no way to start.
Building it answered a week-old puzzle. One bot's server seemed to survive the computer shutting down. The event log showed the computer hadn't shut down in six days, only slept, and the server had been started from a desktop shortcut, outside any agent session, so nothing ever stopped it. The servers that do vanish are the ones that live inside the Claude app.
Servers it starts are cut loose from it and from the Claude app, so they keep running when either closes. For an agent tool that deliberately keeps no start command where the Claude app can find it, it restarts the tool the way the tool's own launcher last did.
Next: usage and pace per project, git state, and audit findings; then a version for every shared library piece and a map of which project uses which.
Platform Engineer