OpenAI makes Codex cloud environments persistent across devices

OpenAI introduced new capabilities for Codex, its software engineering agent, aimed at making it useful beyond a single laptop with reusable cloud development environments accessible from any device. The update, announced at OpenAI’s Dev Day on Tuesday, is one of several for Codex, alongside a refreshed Codex CLI, a new code review experience, tools to harden infrastructure, and other API enhancements.

Codex could already spin up cloud tasks to work remotely, but OpenAI says it is now making those cloud environments more persistent and configurable, rather than treating each cloud task as an isolated remote sandbox. Developers will be able to run Codex wherever they need it — on a computer, remotely from a phone, or in the cloud — and the reusable environments are designed to help tasks start faster while giving teams a shared workspace with approved settings and permissions, OpenAI said.

The Codex CLI is also getting an update that lets developers start and direct tasks using their voice, plus a new “/agents” view meant to make it easier to delegate work and track multiple tasks at once. Other changes include improvements to editing prompts, resuming sessions, and using worktrees, along with a “cleaner” terminal interface OpenAI says is designed to make longer sessions easier to read.

Codex can also be pulled into a new code review experience inside the ChatGPT desktop app, where users can read summaries, explore code changes, or ask Codex about potential issues before sharing feedback on GitHub pull requests or GitLab merge requests — including automatic reviews Codex can perform while users step away from their computers. On the security side, OpenAI is rolling out Codex Security Cloud, a set of tools to help developers scan entire GitHub repositories on demand, on a schedule, or whenever new commits arrive; Codex then investigates findings, removes duplicates, and prepares fixes in the cloud even when the user isn’t active. The toolset includes access to models from OpenAI’s cybersecurity initiative Daybreak Blue without a separate application.

OpenAI also announced several API updates, including a new Decisions API for real-time decision-making that uses Luna to answer user-defined questions with predefined answers, and an updated Agents API that now supports computer use and the ability to use Amazon’s Bedrock Managed Agents to build OpenAI agents that run entirely on AWS.

Why it matters

By making Codex’s cloud environments persistent and shared across a team, OpenAI is pushing coding agents further from one-off remote tasks toward an always-on part of a development team’s infrastructure — raising the stakes on the security tooling it is shipping alongside it.