Guides

How to use Claude Code without installing anything

Claude Code is a terminal program, so it does not need to be on your machine: it needs a machine. On Murmell it is already on the project's one, and you drive it from a tab with your own Anthropic account.

Step by step

1. Open a project. The canvas starts a machine with the CLIs already installed. Nothing to download, nothing to update, and the environment is identical for everyone who opens the link.
2. Connect your Anthropic account. Your subscription or your API key. Usage goes to your account: Murmell resells no tokens and bills for the machine.
3. Open the Claude Code window. A real terminal appears in a window on the canvas. The keys you know work, interrupt and history included, because it is the same program.
4. Close the tab whenever you like. The session lives on the machine, not in the browser. Come back an hour later and the scrollback shows what happened while you were gone.

Why it works

A CLI needs a terminal and a file system. Both exist on the project machine, and a terminal travels to a tab without losing anything. What you see is a real pseudo-terminal, not a reconstruction of one.

What you get on the way

Your disk stays clean. The environment is identical for everybody. And you can open a second window with another agent in the same directory, which a local install makes painful. Running several agents.

The honest limit

You depend on a connection. A remote terminal on an unreliable network is still a remote terminal, and there is no offline mode.

Straight answers