Why not Cursor or VS Code
You already have Cursor, or VS Code with an agent extension, and it works well. So why learn SSH and tmux to do the same job?
Not because one is nicer to use. The difference is architectural, and it only shows up when you are away from your computer.
The difference is architectural, not a preference
An agent inside a GUI IDE is part of that GUI program. It lives in the application's process, its state sits in that window's memory, its output is painted onto that canvas. So it needs a screen, a logged-in desktop session, and a person in front of it. Close the window and the agent ends. Nobody overlooked anything — it grew out of that process.
A CLI agent's interface is a byte stream. Characters in, characters out, nothing graphical anywhere along the way. And a character stream can be attached to, detached from, and attached again. tmux manages that because an 80×24 matrix of characters can be stored whole and redrawn onto any screen — your laptop, your phone, your friend's iPad. Changing device loses nothing. It was only ever characters.
So a CLI agent works remotely for one reason: a canvas of pixels cannot be serialised and reattached, and a matrix of characters can. Nothing to do with being geekier, or with text people being better. It is a difference in capability.
The same scenario, run twice
Say you hand the agent a large refactor at the end of the day. Twenty minutes of work at least, and you are leaving now.
| Cursor left open | tmux + Claude Code | |
|---|---|---|
| Close the laptop | Agent stops | Agent keeps running |
| Two hours later | Open it, context is gone, start again | Open your phone, it's finished |
The right-hand column has nothing to do with how clever the agent is. The session never lived on your laptop. It lives on the machine that was never switched off, and your laptop attached to it for a while. Closing the lid ended the connection, not the work.
Cursor has cloud background agents now, and those do keep running when you close the laptop. What they continue is a copy inside Cursor's own remote sandbox, not the one on your machine. That puts them with the browser agents and Codespaces discussed elsewhere on this site. It does not make them an exception to the left-hand column.
"Couldn't you just use remote desktop?"
This is the most common objection, and in theory it is airtight. The desktop is still on that machine. VNC back into it, Cursor is still open, problem solved.
In practice the two ship different things. VNC sends pixels. SSH sends characters. A full screen update is hundreds of kilobytes to a few megabytes of image data; the same screen as characters is a few kilobytes of text. Three orders of magnitude.
You hit that gap daily. On the train, in a lift, anywhere you are down to one bar, VNC turns into a slideshow and a single scroll takes three seconds to redraw. SSH characters arrive instantly on the same connection.
Even with bandwidth to spare you are still facing a desktop UI built for a mouse and a 1440p display, crammed onto a six-inch touchscreen. Hitting a menu item means zoom, aim, tap. Driving an interface by touch that was never designed for touch is its own punishment.
An honest ending
GUI IDEs are not bad. At your desk an IDE is often the better tool — go-to-definition, refactoring, a debugger, none of which works on a phone. The division is simpler than it looks. An IDE suits "you are here and you are driving". A CLI agent plus remote access suits "it is running and you are checking in". The people who get the most out of either use both: the IDE on the Mac during the day, Agentmux to rejoin the same agent on the same project after they leave.
Agentmux isn't here to replace your IDE. It's here to replace sitting in a chair, waiting.