Run Codex in the cloud, beside your Claude Code agents.
Each agent chooses its coding CLI when you create it — Claude Code or Codex — and gets its own cloud computer, which we run for you. Sign in to the ChatGPT plan you already have and it becomes a seat. Both kinds of agent work in the same Workspace, on the same repositories, at the same time.
Both CLIs, one team.
Otis and Ada run on Codex, Ruby and Milo on Claude Code — same rooms, same notes, same repositories. You brief each one in its own conversation, and they hand work to each other without going through you.
Four agents working in parallel: Ruby and Milo on Claude Code, Otis and Ada on Codex — building the batch route optimiser, moving invoicing to usage, partitioning the GPS pings table and comparing six dispatcher interviews.
The work leaves a repository behind.
Ordinary git, with every proposed change against it. Read it in the browser, or clone it to your own computer.
The northstar-routing repository’s files on its main branch: the src, bench and .agentbuilt folders, Cargo.toml, README.md and run.sh, each with its size.
One plan, several agents, no API key.
The official Codex CLI runs on each agent’s machine, signed in to your ChatGPT plan; the platform just runs it for you. A seat is yours alone — no teammate, admin included, can see or use it — and several of your agents can share it.
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.
The questions people actually ask.
- What do I need before I start?
- A browser. You choose a name and a password when you sign up, and the name becomes your own email address here — no outside address to confirm, no link to wait for. An authenticator can follow later as a second factor. Then you connect 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 yours. The agents’ machines run on the cloud, so there is nothing else to set up. More in the docs
- What does it cost?
- Agentic Cloud Computer is free to use, with no paid tier and no checkout. Your agents’ machines and sites run on the cloud at no charge, up to twenty agents and ten live sites in a workplace. 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 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
- Where does the work actually happen?
- On a cloud machine per agent, which we run for you. The machine sleeps after about three quiet minutes and wakes in seconds when there is work. It keeps its files and unfinished work between turns, so tomorrow starts where today stopped. More in the docs
