How to reach your machines, run Claude Code on them, and keep an agent moving while you are somewhere else.
A turn that dies on your Claude Code usage limit normally waits for a human to come back and send it again. What the limit does to a running session, and how TermLink resends the stopped turn a minute after the limit resets.
Read it →Your TermLink sign-in and your Claude Code sign-in are two different things. Register a personal machine and a work machine under one TermLink account, and see both in the same list — even though each is logged into Claude Code as someone different.
Read it →Four ways to reach an agent on another machine, and what each one costs you: an exposed port, a detached daemon, a streamed desktop, or a relay.
Read it →Paste from the clipboard or drop a file onto the terminal. TermLink uploads it to the machine the agent runs on and types the saved path in for you.
Read it →Keeping three or ten Claude Code agents in one list across your laptop, workstation, and agent box, and telling which one is waiting on you.
Read it →PowerShell eats the Esc key that Claude Code needs, so the TermLink host defaults to cmd.exe on Windows. What that means for your sessions.
Read it →A control-key row, a chat-style message box, and the session still running on your own machine. No app to install on the phone.
Read it →Four ways to stop the prompts, and why auto-accept edits still halts on commands. Which one to pick, and how a long run keeps going while you are away.
Read it →Start Claude Code on your workstation, walk away, and pick it back up from a browser or phone. Install with npm, run the host, no SSH keys, no VPN.
Read it →Install the host with npm, sign in with Google, run one command on the host, and connect from any browser. No SSH keys, no VPN, no open ports.
Read it →