OpenAI announced on Friday it’s launching a research preview of Codex, the company’s most capable AI coding agent yet.

 

Codex is powered by codex-1, a version of the company’s o3 AI reasoning model optimized for software engineering tasks. OpenAI says codex-1 produces “cleaner” code than o3, adheres more precisely to instructions, and will iteratively run tests on its code until passing results are achieved. View More