One mind for your whole space. Nous sees every room, pane, copilot, plan and release train, and reads each pane's progress reports instead of its screen, so it knows what every agent does and what it waits on. You talk to Nous instead of to every agent.
It does the routine work itself: it opens, steers and closes panes, sends them their next step, runs up to five helpers side by side, saves finished work to Space Memory and closes panes whose work is done. Standing orders run around the clock: finished panes are saved and closed, stalled plans get a nudge, and a daily self-review looks back at its own turns.
It brings you only four kinds of decisions: releases, deletes, anything that reaches third parties or money, and the direction of the work. Each decision is a card with Approve and Decline; a plain yes or no in words decides it too. "Always approve" lets a routine kind of decision run on its own next time, never a release or a delete.
You reach it in its dock, on your phone or in a paired Telegram chat. While you are away it keeps a log for your return; at night, requests for your hands wait for the morning; and it spends less while your AI quotas run low, with a cheaper model for its background turns.