In a bid to inject AI into more of the programming process, OpenAI is launching Codex CLI, a coding “agent” designed to run locally from terminal software.

Announced on Wednesday alongside OpenAI’s newest AI models, o3 and o4-mini, Codex CLI links OpenAI’s models with local code and computing tasks, OpenAI says. Via Codex CLI, OpenAI’s models can write and edit code on a desktop and take certain actions, like moving files.

Codex CLI appears to be a small step in the direction of OpenAI’s broader agentic coding vision. Recently, the company’s CFO, Sarah Friar, described what she called the “agentic software engineer,” a set of tools OpenAI intends to build that can take a project description for an app and effectively create it and even quality assurance test it.

Codex CLI won’t go that far. But it will integrate OpenAI’s models, eventually including o3 and o4-mini, with the clients that process code and computer commands, otherwise known as command-line interfaces.

It’s also open source, OpenAI says.

“[Codex CLI is] a lightweight, open source coding agent that runs locally in your terminal,” an OpenAI spokesperson told TechCrunch via email. “The goal [is to] give users a minimal, transparent interface to link models directly with [code and tasks].”

In a blog post provided to TechCrunch, OpenAI added, “You can get the benefits of multimodal reasoning from the command line by passing screenshots or low fidelity sketches to the model, combined with access to your code locally [via Codex CLI].”

To spur use of Codex CLI, OpenAI plans to dole out $1 million in API grants to eligible software development projects. The company says it’ll award $25,000 blocks of API credits to the projects chosen.

AI coding tools come with risks, of course. Many studies have shown that code-generating models frequently fail to fix security vulnerabilities and bugs, and even introduce them. It’s best to keep that in mind before giving AI access to sensitive files or projects — must less entire systems.