Claude Code in the cloud

Claude Code in the cloud

A cloud VM per project with Claude Code signed in, your repo cloned and your app on a real URL.

To run Claude Code in the cloud, give it a machine of its own. homemade starts a Linux VM for each project or task with Claude Code already installed and signed in to your Claude plan or API key, your repo cloned and your app running behind a preview link. It keeps going when you close your laptop, you can check on it from your phone, and it sleeps when idle so you stop paying for it.

The facts

What every VM comes with.

FactDetails
Claude CodeInstalled on every VM. Use your Claude subscription or an Anthropic API key.
MachineA Linux VM with its own kernel and disk. Sizes from 0.5 vCPU / 1 GB up to 16 vCPU / 32 GB.
AgentsClaude Code, Codex, OpenCode, pi, Kimi and Grok installed. Sign in once and every new VM starts signed in.
LinksA URL for every port a service listens on. Public, team only or owner only.
SleepSleeps when idle and wakes where you left it, files and terminals included.
AccessBrowser terminal (phone too), SSH, VS Code, Cursor, the CLI, an MCP server and an HTTP API.
PriceHobby is free: 25 VM-hours a month, 1 VM at a time, nano or tiny. Pro is $20/mo with $20 of usage included, then from $0.012 an hour (nano) to $0.18 (large) by size. Sleeping VMs don't use hours.

How to start

  1. Sign in once

    Open Account → AI tools and sign in with your Claude plan, or add an Anthropic API key.

  2. Start a VM per task

    Connect a GitHub repo (or start from a template). Each VM starts with the repo cloned at the branch you pick, your install commands run and your services started.

    Terminal
    homemade vm create --branch fix-auth --wait
  3. Run Claude Code

    Open the VM's terminal in the browser or over SSH and run claude. Open the preview link to see the app it's changing.

    Terminal
    homemade ssh misty-fern-142claude

When something else fits better

homemade isn't the right tool for everything.

  • Fire-and-forget tasks

    If you want to hand off a task from the Claude app and get a pull request back, without a running app to look at, Anthropic's own cloud sessions do that.

  • Your machine is always on

    If your own computer is always on and you only want to steer it from your phone, Claude Code's Remote Control is enough.

  • One box, run by you

    If you want one server you manage yourself for years, a plain VPS is cheaper per month at full uptime.

Questions

Can I run Claude Code in the cloud with my own Claude subscription?

Yes. Every homemade VM has Claude Code installed. Sign in once under Account → AI tools, with your Claude plan or an Anthropic API key, and every VM you create starts signed in.

Is this better than a VPS for Claude Code?

A VPS works if you want one long-lived server and you're happy to install, secure and update it yourself. homemade gives you a fresh VM per project or task with the agent signed in and your app running, a link per port, and sleep when idle, so you don't pay for a server that sits there.

Can I use Claude Code from my phone?

Yes. The terminal and chat work in a phone browser. The agent runs on the VM, so it keeps working when your phone locks or your laptop is closed.

Can I run several Claude Code agents in parallel?

Yes. Start one VM per task on its own branch. Each has its own files, ports and preview links, so agents don't step on each other. Heavy use of one subscription across many VMs can hit Anthropic's rate limits; an API key avoids that.

What happens when I stop using it?

When a VM is idle it goes to sleep and keeps its disk and running state. You pay for hours it runs, not hours it sleeps.

Read on

Try it on the free plan

Hobby is free. Connect a repo and your first VM starts from it.