OpenAI's Codex gets reusable cloud environments, voice CLI at Dev Day

OpenAI's Codex updates arrive as the company pushes the coding agent beyond a single developer's laptop. Previously, Codex could already spin up cloud tasks to work remotely, but each task was treated as an isolated remote sandbox. The new reusable cloud development environments make those spaces persistent and configurable, giving teams a shared workspace with approved settings and permissions. This change matters because it lets developers run Codex wherever they need it — on a computer, from a phone, or in the cloud — and is designed to help tasks start more quickly.

The broader package announced at Dev Day touches several parts of the developer workflow. The Codex CLI update adds voice control and a /agents view for delegating tasks, while a cleaner terminal interface aims to make longer sessions easier to read. Codex is also pulled into a new code review experience within the ChatGPT desktop app, where users can read summaries, explore changes, or ask Codex about potential issues before sharing feedback on GitHub pull requests or GitLab merge requests. Automatic reviews let Codex perform an initial pass while users step away from their computers.

On the security side, Codex Security Cloud is designed to help developers secure infrastructure by scanning GitHub repositories and preparing fixes in the cloud even when the user is inactive. The toolset notably includes access to models offered through OpenAI's cybersecurity initiative Daybreak Blue without a separate application. Whether teams adopt these features may hinge on how the approved settings and permissions work in practice, and on whether the automatic code reviews and security scans prove useful enough to change existing workflows.