Running Claude Code on a remote machine — and checking on it from your phone
Start Claude Code on your workstation, walk away, and pick the conversation back up from a browser or phone. How Auto-Yes keeps a long run moving while you are gone.
Claude Code runs in a terminal on one machine. That is fine while you are sitting at it — and awkward the moment you are not. The agent is mid-refactor on your workstation, you have to leave, and the session is stranded wherever you launched it.
TermLink puts that terminal behind your Google account, so the machine keeps running the agent while you watch it from wherever you are.
The session belongs to the machine, not to you
This is the part worth understanding, because everything else follows from it.
When you run termlink host on a machine, that process owns the terminal. Claude Code runs inside it. Your browser is only a window onto that terminal — so closing the tab, shutting your laptop, or losing signal in a tunnel does not touch the agent. It keeps working.
When you come back and reconnect, TermLink repaints the screen exactly as the agent left it. Claude Code draws a full-screen terminal UI, and it survives the round trip intact:
The one thing to know: this is not tmux. TermLink does not detach the session into a background daemon. The termlink host process on that machine has to stay running — if you kill it, or the machine sleeps, the agent goes with it. Leave it up on the machine you actually want the work to happen on.
Auto-Yes: the reason a long run does not stall
Claude Code stops and asks before it runs a command. Sensible when you are watching. Useless when you are not — you come back after lunch and find the agent has been sitting on a permission prompt for forty minutes.
Toggle Auto-Yes on a session and TermLink watches for that prompt — the numbered menu with 1. Yes and a No option — and confirms it, so the run keeps moving.
Two things to be honest about, because they decide when you should use it:
- It confirms the highlighted option. It does not read the command and judge whether it is a good idea. Normally the highlight sits on
Yes, which is what you want — but it is a convenience, not a safety review. - Free-form questions are left alone. When Claude asks something open-ended rather than offering a Yes/No menu, the session waits for you. That is deliberate.
So: turn it on for a test run, a refactor, a build you trust. Leave it off when the agent is doing something you would not want auto-confirmed. It is a per-session toggle and it starts out off.
Prompting from a phone, like a chat
On a phone, the terminal gets a message box at the bottom — type, hit send. It reads like texting a colleague, except the colleague is a shell.
That changes the shape of the work. You check what the agent did over lunch, type the next instruction, and send it. It picks up. You are not "remoting into a computer"; you are continuing a conversation.
You can also paste or drop an image onto the terminal — a broken layout, a stack trace, a design mock. TermLink uploads it to the host machine and types the saved path into the prompt for you, so your next message can just point Claude at the file.
What you do not get, and I would rather say it plainly: there are no notifications yet. Nothing pings you when the agent finishes or gets stuck. What you get instead is a glanceable list — each machine card shows that session's most recent Claude message, so you can tell at a glance which agent is still working and which one is waiting on you.
Several agents, one list
The list is the point once you are running more than one.
Register as many machines as you like — your laptop, a workstation under the desk, a box that exists only to run agents. Each one shows up as a card with its latest message, and you switch between them the way you switch between chats. Whether the sessions live on one machine or ten does not change how you work with them.
For a team running a fleet of agents, that is the whole pitch: one place to see what every agent is doing, from any device, without giving anyone SSH access to anything.
Putting it together
On the machine where your code lives:
termlink login # once, with Google
termlink host # leave this running
Then from anywhere — the web client in a browser, or termlink client from another terminal — pick that machine, run claude, and flip Auto-Yes on if the job is one you trust to proceed on its own.
Then close the tab. The agent does not care.
New to TermLink? Start with Getting started with TermLink — signing in, registering a machine, and connecting to it.