Agent orchestrators are the IDE dream repackaged. IDEs never really took off, excepting lock-in/monolopolization (Visual Studio, Xcode). They never lived up to the grand vision of the likes of Alan Kay. IDEs of today are still basically just text editors with a file explorer. Agent orchestrators seem similar. The vision is grand but the implementation is just tabbed terminals.

I think IDEs took off plenty well, but several got frozen in time.

Visual Studio as the IDE for building windows client apps, especially WinForms, was and still is a genuinely incredible and productive experience. The ease of which you could click-and-drag a UI, context switch to logic in the code behind the forms, wire up a web service backend, share domain models and have navigation and search tools understand all of it was great. And the TFS integration was quite good too. You really only had to leave VS to do database work or administer some IIS pools.

Unfortunately, it couldn't keep up with the rest of the dev world. "Server Explorer" morphed to include your Azure VMs but froze for 30s each time you opened it. Docker tools came in super late, most Azure services didn't really have a VS tooling experience. The "right click publish" workflow meant for small systems never figured out how to graduate to real-world needs across many teams. Developers had to learn how to use many other tools for modern stuff, and so VS became far less of a center of gravity, often to their annoyance.

I think they definitely have the IDE vision in mind and are trying to move off of terminals, based on two parts of the original article

> so you can close the application, reconnect from another device, and pick up exactly where you left off.

I think this is the remote IDE development dream that no one could quite get right, partly because there wasn't enough reason to run things on a 24/7 device. I think with coding agents that can run in the background this changes.

> Sessions can be accessed through the web and native macOS/iOS applications, and sharing a live session with other people is built in from the start.

I'd really like to point out that "Sharing a live session" is horrible UX for a terminal multiplexer because the terminal has to be the same size (# of rows/cols) on all viewers' screens, and some of these viewers may be on a phone and others on a laptop. Believe it, I tried myself and there's no good way around the problem.

What is interesting is that they added this sentence anyway. This tells me that their long-term endgame is not the terminal. They're most likely trying to build a GUI-based agent IDE and then eventually expand to other work (per their headline of being the "multiplexer for all work") as it all gets more and more agent-based anyways. Well, they're not alone in having that vision.