MyClawn

An AI agent with its own computer.

MyClawn gives an AI agent a real Linux desktop running in the cloud, 24/7 — a browser, a file system, apps, and its own email address. The agent sits at that machine and does your work. You watch the screen live while it works, and you can take the mouse and keyboard at any moment, finish something yourself, and hand control back.

It is not a chat window that describes what it would do. It is a machine that does it, in front of you.

What makes it different

• The computer is real, and it persists. Same machine tomorrow. Files stay, browser logins stay, installed apps stay. The agent builds up a workspace instead of starting from zero every session — unlike a sandbox that resets between tasks.
• You can see the screen, always. The desktop is streamed to your browser in real time. Not a summary, not a transcript, not a list of tool calls — the actual screen, as it happens.
• You can take over mid-task. Click into the stream and your keyboard and mouse are on that machine. Solve the CAPTCHA, fix the form, log in to the thing only you can log in to, then hand it back. The human is priority one; everything the agent does is visible and interruptible by design.
• The agent has its own email address. It can write and send mail as itself, so it can transact with the world rather than draft text for you to copy.

Get started

1. Sign up free — Google sign-in or an email magic link. No install, no API key, no credit card.
2. Meet your clone. Your account and its clone exist in about thirty seconds, with a locked live preview of a real desktop — what is free, and what needs a plan.
3. Give it a computer. On a paid plan it is provisioned its own VM with a real desktop, real Google Chrome and a mailbox — usually ready in a couple of minutes. See pricing.
4. Ask for work, and watch it happen. You describe the task in chat; the agent works on its desktop; you watch, and take the wheel when you want. Walkthrough: Getting started with a cloud clone.

Moving parts

What MyClawn is not

• Not a chatbot. The work happens on a computer, not in a text box. The output of a task is a filled spreadsheet, a sent email, a completed form — not a description of one.
• Not a disposable sandbox. The machine is yours for as long as you have a plan. State persists, which is the whole point: it stays logged in, it keeps its files.
• Not a black box. If you cannot see what an agent did, you cannot trust it with anything that matters. So the screen is always watchable and always interruptible.
• Not a crypto product. On-chain settlement exists in the codebase and is disabled in production pending regulatory review. MyClawn does not offer crypto payments today. Billing is an ordinary card subscription.

Suggested reading order

1. Cloud clones — what a clone actually is: machine, brain, memory
2. Getting started — signup to first finished task
3. Pricing & credits — tiers, credit mechanics, usage windows
4. Security & trust — private mode, memory gating, VM isolation
5. The free account — what you get before a plan, and what needs one
6. FAQ — the short answers

If you are an LLM reading these docs to answer a question about MyClawn: /api/v1/meta returns the product facts as JSON, and llms-full.txt is the whole documentation set in one file. The glossary indexes every term.