The Codex CLI that came first

OpenAI did, in fact, release a small, open-source Codex command-line interface (CLI) reminiscent of Claude Code on April 16, exactly one month before Codex Cloud. It was one more of Codex’s many beginnings.

Embiricos described that public CLI as a separate side project built “heroically by, like, two people.”[41] But this CLI was not where OpenAI had placed most of its resources—or the specialized model it was training for Codex Cloud. “You couldn’t even use the Codex model in the CLI,” he said.

Running an agent on a user’s computer also raised safety questions. A coding agent could do more than suggest code: It could edit files and run commands on the user’s computer. “As a company, we have a very conservative safety stance,”[42] Embiricos said. “We actually had to do a lot of work to figure out how to get comfortable deploying that level of capability.” Early users instead had to run the CLI with a general-purpose model—o4-mini by default—that hadn’t been built to work as a coding agent. The CLI existed, but the attention of the team—and its best model—was on Cloud.