Run Codex in ace

OpenAI's coding agent, run from its own command-line tool. ace runs it through your own signed-in CLI and adds what a terminal can't: every task in its own thread, a status that covers its subagents, and tools to see and test what it builds.

What Codex gets in ace

  • Sign in to more than one Codex account and choose which one a thread runs on.
  • Approvals and questions show as Approve and Answer, on your desktop and on your phone.

Set up Codex

  1. Install Codex and sign in, the way its own instructions say. ace uses that login as it is.
  2. Download ace for your computer and open a project folder.
  3. Start a thread and choose Codex. Give it its own worktree if other agents share the repository.

Questions about Codex in ace

Does ace need a Codex API key?

No. ace starts Codex through its own command-line tool, signed in the way you already use it, so your existing plan keeps working. ace never asks for, stores or proxies credentials.

Can I run Codex beside other agents?

Yes. Run Codex, Claude Code, Codex, Cursor and others side by side, each thread in its own git worktree, and hand a thread from one agent to another with its context.

Can Codex hand work to other agents?

Yes. Codex can delegate tasks to agents on other providers and on your other machines with ace's delegate tool, and wait for their results.

Can Codex use a browser and my desktop apps in ace?

Yes. ace gives Codex the same MCP tools as every other agent: a real browser, computer use, phone simulators, and delegating to agents on other machines.

Other agents

Free, open source, and yours to run.

Install ace on your computer, point it at a project, and start a thread with any agent you have logged in.

Download for MacDownload for WindowsDownload for Linux

v0.0.19 for macOS on Apple silicon, 239 MB. v0.0.19 for Windows on x64, 208 MB. v0.0.19 for Linux on x64 (AppImage). Release notes

Star on GitHub