Codex CLI
Codex CLI is OpenAI’s coding agent for the terminal. YOLO Studio gives it a secure cloud workspace of its own: Codex comes pre-installed, runs in an isolated lane next to your other agents, and keeps working while you are away from your desk.
Get startedEvery workspace is a secure Linux sandbox running in its own virtual machine. The agent works on your repository inside it, as a non-root user, with your files kept between sessions. It cannot reach your laptop, your other projects or anyone else’s workspace.
Turn on YOLO Mode and Codex stops asking for permission before each command. That is far easier to say yes to when the blast radius is a sandbox built for the job rather than the machine with your SSH keys on it.
Start an agent in its own lane and it gets its own git clone on a lane/<name> branch, so agents working side by side never share a git index or step on each other’s changes. The Quick Lane button starts your primary agent in a fresh lane in one click.
Restart & Resume restarts Codex and picks the conversation back up. Codex can also drive the workspace itself through YOLO Studio’s MCP server: opening tiles, publishing artifacts and managing Kanban boards.
Run your app in a preview tile next to the agent. When the agent saves a file, the preview reloads, and one command ships what is in the preview to a yolo.host address.
Connect a GitHub repository (or host one inside YOLO) when you create the workspace. It is cloned and configured for you, so git commit, git push and gh pr create work in the agent’s session without extra setup.
Sign in with GitHub, choose New Workspace, and pick the repository to work on. The sandbox is ready in seconds.
Choose Codex CLI from the tile picker. It is already installed in the sandbox, so there is nothing to download. Pick the main workspace or a new lane to run it in.
Connect your ChatGPT subscription or an OpenAI API key from Agent access. Credentials are delivered to the session, never shared with other workspaces or users.
Type into the tile, or drag files onto it. The shortcut bar sends common follow-ups in one click: Commit & Push, Pull Latest, Merge to Main and Continue.
One agent in a terminal is where most people start. In YOLO Studio, Codex can also be one of several workers. Describe the work and it becomes cards on a Kanban board; the Background Runner then dispatches ready cards into isolated lanes, up to four at a time, waits on cards that depend on unmerged work, and lands results the way you choose: by hand, as a pull request for review, or merged automatically.
You can also require an agent review: a different model checks each result before anything relies on it.
No. You can connect a ChatGPT subscription instead, or use an API key if you prefer. Either is set up once from Agent access.
Yes. Claude Code, Codex CLI and Gemini CLI are all pre-installed, and other agents such as GitHub Copilot, Aider, Goose and Qwen Code install the first time you pick them. Put each one in its own lane and they work on the same repository without colliding.
The agent runs in the cloud workspace, not on your machine, so closing the lid does not stop it. Work queued on a Kanban board keeps moving through the Background Runner while you are away.
Sign in with GitHub, open a workspace on your repository, and put your first agent to work in a few minutes.
Get started
