OpenAI Codex Cloud: Reusable Dev Environments for Any Device

OpenAI Codex Cloud Brings Reusable Dev Environments to Every Device

OpenAI Codex cloud now supports reusable development environments that developers can access from any device. The update makes Codex more useful beyond a developer’s laptop by turning cloud tasks into persistent, configurable workspaces instead of isolated remote sandboxes.

Announced at OpenAI’s Dev Day on Tuesday, the change is one of several for Codex. OpenAI also introduced a refreshed Codex CLI, a new code review experience, tools to harden infrastructure, and other API enhancements.

According to OpenAI, developers can now run Codex wherever they need it — whether on a computer, remotely from a phone, or in the cloud. The reusable development environments are designed to help tasks start more quickly and give teams a shared workspace with approved settings and permissions.

While Codex could already spin up cloud tasks to do work remotely, the new approach makes those environments more persistent and configurable rather than treating each cloud task as an isolated remote sandbox.

Codex CLI Gains Voice Control and a New Agents View

The Codex CLI is getting an update that allows developers to start and direct tasks using their voice. A new /agents view is meant to make it easier to delegate work and track multiple tasks at the same time.

Other changes include improvements to everyday tasks such as editing prompts, resuming sessions, and using worktrees. OpenAI is also rolling out a cleaner terminal user interface designed to make longer sessions easier to read.

For developers who spend hours in the terminal, the voice control addition could reduce friction when switching between tasks or issuing quick instructions. The /agents view, meanwhile, targets teams juggling several parallel workstreams at once.

Code Review Inside the ChatGPT Desktop App

Codex can also be pulled into a new code review experience within the ChatGPT desktop app. There, users can read summaries, explore code changes, or ask Codex about potential issues before sharing feedback on GitHub pull requests or GitLab merge requests.

Automatic code reviews also let Codex perform an initial review while users step away from their computers. That means a developer can return to a summary of suggested changes rather than starting the review process from scratch.

The feature is aimed at teams that want faster feedback loops without abandoning existing review workflows. Feedback still flows through GitHub pull requests or GitLab merge requests, so the usual collaboration channels stay intact.

Codex Security Cloud Scans Repositories Automatically

On the security side, OpenAI is rolling out a new set of tools called Codex Security Cloud, designed to help developers secure their infrastructure. Developers can use the tools to scan entire GitHub repositories on demand or on a regular schedule, as well as whenever new commits arrive.

Codex will then investigate findings, remove duplicates, and prepare fixes in the cloud — even when the user isn’t active and their laptop is closed.

Notably, the toolset includes access to the models offered through OpenAI’s cybersecurity initiative Daybreak Blue, without requiring developers to submit a separate application. For security teams, that removes an onboarding step that could otherwise slow down adoption.

API Updates: Decisions API and Agents API

OpenAI also announced several API updates. A new Decisions API handles real-time decision-making by using Luna to answer a set of user-defined questions with predefined answers.

The company also introduced an updated version of the 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.

These API changes matter for developers building agent-based products on top of OpenAI’s stack. The Decisions API targets scenarios where speed and consistency matter, while the updated Agents API extends where those agents can run.

What the OpenAI Codex Cloud Update Means for Developers

While Codex could already spin up cloud tasks to do work remotely, the shift toward persistent, reusable environments signals a broader push to make the agent a shared team tool rather than a personal assistant tied to one machine.

For teams already standardizing on approved settings and permissions, that shared workspace model could reduce setup time on every new task. Instead of recreating a sandbox each time, teams can work from an environment that already reflects their configuration.

The combination of voice-enabled CLI controls, in-app code review, automated security scanning, and expanded API options points to a single goal: keeping Codex useful whether a developer is at a desk, on a phone, or away from their computer entirely.

For now, the updates are available through OpenAI’s announced channels, and developers evaluating Codex for team use will want to review how the new permissions and shared environment settings fit their existing workflows.