OpenAI adds reusable cloud environments to Codex — TechCrunch
OpenAI has introduced new capabilities for its Codex software engineering agent, including reusable cloud development environments accessible from different devices. The update was announced during Dev Day on Tuesday. As TechCrunch reports, the company also updated the Codex CLI, code review tools and infrastructure security features.
Shared cloud environments
Previously, Codex could already run tasks in the cloud for remote work. OpenAI is now making such environments more persistent and customizable, rather than separate isolated environments for each task.
Developers will be able to run Codex on a computer, remotely from a smartphone or in the cloud. Reusable environments are expected to speed up task launches and provide teams with a shared workspace with approved settings and permissions.
The updated Codex CLI makes it possible to start and direct tasks by voice. It will also feature a /agents section for delegating work and tracking multiple tasks simultaneously. Other changes include prompt editing, session resumption, worktree support and a simplified terminal interface for longer sessions.
More current news is available on the UA.News Telegram channel Telegram.
Code review and security
Codex can be used in a new code review tool in the ChatGPT desktop app. Users will be able to review summaries, examine code changes and ask Codex about potential issues before sharing feedback on a pull request in GitHub or a merge request in GitLab.
Automated code reviews will allow Codex to perform an initial review while the user is away from the computer. OpenAI is also launching the Codex Security Cloud toolset to protect infrastructure. It can scan entire GitHub repositories on demand, on a schedule or after new commits appear, analyze identified issues, remove duplicates and prepare fixes in the cloud.
Codex Security Cloud includes access to models from OpenAI's Daybreak Blue cybersecurity initiative without a separate application. In addition, the company announced the Decisions API for real-time decision-making and updates to the Agents API with support for computer use and Amazon Bedrock Managed Agents for building OpenAI agents that operate entirely in AWS.
