Run Claude Code in the cloud, on the plan you already have.
Agentic Cloud Computer runs Claude Code in your own cloud account, with everything it needs built in: git with CI/CD, hosting, storage, email, notes and memory. Sign in to your Claude plan once and it becomes a seat: no API key, no per-token bill.
It ends live, not at a pull request.
Git made for agents, hosting, storage and email are already here. What your agent finishes goes live at its own address, with nothing for you to set up.
Sites: the dispatcher app and the routing service, both running around the clock, and the docs site, each live at its own address and each last published by an agent.
It runs on the subscription you already pay for.
The official Claude Code, on a cloud machine of its own, signed in to the Claude plan you already have. Every agent on it runs on that plan, and the bill stays between you and Anthropic. Each seat shows how much of its five-hour and weekly windows is spent, with a mark where an even pace would be by now.
Subscriptions: the four sign-ins this workplace holds — two Claude Max 20x seats and two ChatGPT Pro 5x seats — each with its usage in the current five-hour and weekly windows, and a mark on the ones agents are working on right now. Under them the first Claude seat's usage: the five-hour window at 46 percent and the week at 68 percent, each with a mark showing where an even spend would be by now.
It can build and test. It cannot decide.
Protected changes come back as a proposal with the exact diff and its checks. An agent can prepare the work; approving it is yours.
Proposal #41 in northstar-routing, waiting for you: Ruby proposed it from branch batch-optimiser into main; her write-up with the benchmark, fourteen files changed, six commits, checks passed, and the Approve and Reject buttons.
The questions people actually ask.
- What do I need before I start?
- Your company’s own cloud account and a domain for it, plus an update key and a licence from us. Setting it up is about fifteen minutes of work, then a wait for your cloud provider, which can take an hour or more. Then each person connects an AI subscription — a Claude plan, which the official Claude Code uses, or a ChatGPT plan, which the official Codex CLI uses — and it stays theirs. More in the docs
- What does it cost?
- The first month is a free trial. After that your own Agentic Cloud needs a licence from us, which covers upgrades and support. Your cloud provider bills your account directly for what it runs, your Claude or ChatGPT plan is billed by Anthropic or OpenAI, and any other service you connect bills you directly. More in the docs
- How is it different from running Claude Code or Codex myself?
- The same official CLIs, with everything around them already there: git, hosting, storage, email, notes and memory. Many work at once, they share what the team wrote down, and a change to protected code waits for your yes, from your phone if you like. More in the docs
- How does an agent use my API keys without seeing them in a chat?
- You save a key once, in the Workspace’s Secrets section, with a line on what it is for. The value goes straight into storage. When an agent works, the key is placed in its machine’s environment, so the command that needs it reads the value while the agent works with the name, and the value is stripped from its transcript and activity. A key belongs to the room it was saved in, so an agent in another room cannot use it. More in the docs
Give Claude Code its first job today.
