Rooster Wake

Rooster Wake is for a computer that should be asleep by default, awake while it is used, and reachable when you need it — answered by name from any Claude chat.

With one laptop and nothing else on the network, Claude can put it to sleep from anywhere, hold it awake while a long job runs, say whether it is up, and, on Windows, start Claude Code in a folder you registered and hand you the live session in the Claude app.

Ask Claude for the sign-in link: every dashboard row carries Remote Desktop and SSH… too. Remote Desktop wakes the computer, holds it while you sign in and hands you to Chrome Remote Desktop with it listed online. SSH… sets SSH up from the dashboard, authorises a key for the computer you are on, and Connect wakes, holds and opens PuTTY, WinSCP or your SSH app signed in. Both keep it up for the session and let it sleep ten minutes after.

Waking a machine that has slept needs a second device — a sleeping PC cannot wake itself, so the wake comes from something on your network that stays on: an Amazon Echo, through the free skill; the same free agent on a NAS, a Home Assistant box or a Pi; or an open-source dongle you build. Without one, sleep it from Claude and wake it at its keyboard or lid.

Ten tools: list, status, wake, set up waking, hold, release, start and stop Claude Code, sleep (always asks you first), a sign-in link. No shutdown tool, deliberately.

Getting set up: ask Claude to "list my machines" — with nothing installed yet the answer is the one command that installs the free agent on the PC you want to reach, filled in with your account. Run it there, ask again. Remote AI sessions also need Claude Code signed in there (your install, your Anthropic account — we start and stop the process, never see the conversation). Waking is free on every plan; free includes ten sleeps and ten Remote AI sessions a month, and paid plans are unmetered and add the hold, restart and shutdown. Full walkthrough: https://roosterwake.com/run-claude-code-remotely