Hosting

Claude Code in the cloud
that never forgets

Give Claude Code its own machine. It keeps working when your laptop is closed, keeps its files and session history, and answers from anywhere.

No newsletter. One email when your access is ready.

Run the agent you already use
Claude CodeCodexOpenClawCursorHermesZeroClaw
Bring your own model
AnthropicOpenAIGoogleDeepSeekMoonshot
Or your own container, and hundreds of models through OpenRouter.

What it gets you

Its own machine

Each agent gets a private virtual machine with 2 vCPU, 2 GB of memory and an 8 GB disk. Nothing is shared with other agents.

Sessions that survive

The conversation, the files and the installed packages are still there next week. It picks up exactly where it stopped.

Your key or your subscription

Run it on your Anthropic API key, or sign in with your Claude Pro or Max plan from the agent's terminal.

Sleeps, then wakes in 0.08 s

After five quiet minutes it sleeps and frees its slot. Your next message wakes it before you notice.

Rewind in one click

A checkpoint every 15 minutes. If it breaks something, put the whole machine back as it was.

A spend cap

Each agent has a budget. At the cap it stops cleanly and tells you.

Close the laptop.
Claude keeps its workspace.

Start a refactor before you leave. Claude Code keeps going on its own machine, with the repository, the packages it installed and the session. Tomorrow you ask how it went, from Telegram or your terminal, and it answers with the full context.

0.12s
to start a new agent
0.08s
to wake a sleeping one
0.14s
to rewind to a checkpoint

Questions
and answers.

Keep
reading.

You ship the agent.
We keep it running.