Skip to main content

OpenAI Expands Codex Capabilities with Persistent Cloud Environments

The company revealed new capabilities for its Codex software engineering agent at Dev Day, enabling developers to access reusable cloud development en

2 min read2 views5 tags
Originally reported bytechcrunch

The company revealed new capabilities for its Codex software engineering agent at Dev Day, enabling developers to access reusable cloud development environments from any device, extending the tool's utility beyond a local laptop.

This announcement marks one of several updates for Codex, which also includes a refreshed Command Line Interface (CLI), a new code review experience, infrastructure hardening tools, and various API enhancements.

Although Codex previously spun up cloud tasks for remote work, today's update makes these environments more persistent and configurable, moving away from treating each cloud task as an isolated sandbox.

Developers can now run Codex on computers, phones, or in the cloud, according to the company. These reusable environments are designed to accelerate task initiation and provide teams with a shared workspace featuring approved settings and permissions.

Additionally, the Codex CLI has been updated to allow developers to initiate and direct tasks using voice commands.

The update introduces a new /agents view to streamline delegating work and tracking multiple tasks. Improvements to prompt editing, session resuming, and worktree usage have been made, alongside a redesigned terminal user interface for better readability during extended sessions.

Codex is being integrated into a new code review experience within the ChatGPT desktop app, allowing users to review summaries, explore code changes, and query potential issues before providing feedback on GitHub pull requests or GitLab merge requests.

Automatic code reviews enable Codex to conduct an initial assessment while developers are away from their machines.

To bolster security, OpenAI has introduced Codex Security Cloud, a suite of tools to help developers secure their infrastructure. This allows for on-demand or scheduled scanning of entire GitHub repositories and automatic investigation of findings, including duplicate removal and fix preparation, even when the user is offline.

Notably, this toolset provides access to models from OpenAI's Daybreak Blue cybersecurity initiative without requiring developers to submit a separate application.

The company also unveiled several API updates, including a new Decisions API for real-time decision-making utilizing Luna to answer predefined questions against user-defined inputs. Furthermore, the Agents API has been updated to support computer use and the integration of Amazon's Bedrock Managed Agents to create OpenAI agents running entirely on AWS.

#AI News#Codex#Cloud environments#Code review#API updates
ES
Editorial StaffEditor

The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.

View all posts
Reader feedback

What did you think of this story?

User Comments

Filter:
No comments yet. Be the first to comment!
Continue reading
View all news