Multi-harness workspace
A browser-based, multiplayer workspace that runs agent CLIs on a team runner.
Teams that need shared terminals, previews, review comments, and persistent remote sessions.
Teams that need shared terminals, previews, review comments, and persistent remote sessions.
Execution depends on a connected self-managed or AQ-managed runner, and the GUI implementation is not public.
Existing evidence gates classify four predefined workflows. Bands are non-numeric and do not rank product quality.
Stay close to one coding session and inspect changes in a dedicated visual surface.
Current sources document visual review, workspace isolation.Run several coding tasks on one machine without their branches or files colliding.
Current sources document parallel sessions, workspace isolation, visual review.Start or revisit coding work away from the machine where the repository is running.
Current sources document remote execution or access, shared team access.Let teammates enter the same live workspace to watch, steer, preview, or review work.
Current sources document remote execution or access, shared team access, workspace isolation, visual review.Unknown means the current first-party record does not establish the mechanism; it is not converted into evidence of absence.
Multiple workspaces and agents can run concurrently.
Each workspace receives its own Git worktree and branch.
The browser workspace includes an editor, live previews, comments, and PR state.
Persistent sessions run on a runner VM and survive browser or laptop disconnects.
Teammates can enter the same live terminal, editor, and preview.
Implementation inspection and source-native activity provide investigation context. Neither changes workflow fit.
The GUI implementation is proprietary. Current claims rely on first-party product documentation rather than a public-code inspection.
Sources establish specific current GUI claims; their count does not add fit points.
