OpenAI has just released a new macOS application to help code better with its state-of-the-art Codex technology. This new app combines all of the most popular agentic practices over the last year into one. It offers developers a more customizable interface for tapping into the capabilities of OpenAI’s GPT-5.2-Codex coding model. The app’s launch comes just weeks after the launch of GPT-5.2-Codex introduced in early August.
On launch day June 23, 2026, a media event in Boston, Massachusetts celebrated the launch. During a recent event on AI’s impact on jobs, Sam Altman, OpenAI’s CEO, bragged up GPT-5.2’s dramatic skills. He stated, “If you really want to do sophisticated work on something complex, 5.2 is the strongest model by far.” Altman elaborated on the importance of usability, noting, “It’s been harder to use, so taking that level of model capability and putting it in a more flexible interface, we think is going to matter quite a bit.”
Russell Brandom, one of today’s leading tech journalists, has been writing about the tech industry since 2012. He noted that GPT-5.2 is now the best performer on TerminalBench, a test of AI’s ability to perform command-line programming tasks. This award opens up exciting opportunities for GPT-5.2-Codex in a competitive landscape, especially as OpenAI looks to lure users away from Claude Code.
The integration of agentic practices within the new macOS app represents OpenAI’s ongoing commitment to refining user experience while leveraging cutting-edge technology. As developers increasingly seek tools that simplify complex tasks, this app could play a significant role in reshaping how coding is approached.
OpenAI’s strong strategic focus on improving usability fits a trend seen across many other tech industries toward more natural interfaces. The expansion is part of the company’s goal to bring its most advanced coding model to the macOS app. Hopefully, this change would open the door for a larger user base and bring over users currently on alternative platforms.