AI··1 min readTechnical readSource-backed

OpenAI Updates Codex With Reusable Cloud Development Environments and New CLI Voice Capabilities

OpenAI announced updates for its Codex software engineering agent during Dev Day on Tuesday.

By
WIREUNWIRED BRIEF

OpenAI announced updates for its Codex software engineering agent during Dev Day on Tuesday. The primary addition is reusable, persistent, and configurable cloud development environments accessible from any device, allowing teams to share a workspace with approved settings and permissions while helping tasks start more quickly. Additionally, the refreshed Codex CLI supports voice-directed tasks, a new /agents view for tracking multiple tasks, improved prompt editing, session resumption, worktrees, and a cleaner terminal user interface.

Codex integration with the ChatGPT desktop app now provides a new code review experience for GitHub pull requests and GitLab merge requests, including automatic reviews. For security, OpenAI introduced Codex Security Cloud to scan entire GitHub repositories on demand, on a regular schedule, or upon new commits, which investigates findings, removes duplicates, and prepares fixes in the cloud while incorporating models from OpenAI’s Daybreak Blue cybersecurity initiative.

Furthermore, OpenAI revealed API updates featuring a new Decisions API utilizing Luna for real-time decision-making and an updated Agents API supporting computer use and Amazon’s Bedrock Managed Agents for building AWS-based OpenAI agents.

STORY JOURNEY

The story so far

Earlier coverage connected by shared names and topics. Follow the dates to see how coverage developed; these links do not imply every article describes the same event.

  1. GettyImages 2213954141 1152x648 1
    Florida invokes extinction fears in legal bid to halt OpenAI development

    The state of Florida has filed a legal motion seeking a temporary injunction to halt OpenAI from continuing to develop frontier AI…

    Connected by: ChatGPTEARLIER COVERAGE
  2. OpenAI Apologizes to Australia After Experimental AI Agents Breached Multiple Government Websites in June

    OpenAI apologized to the Australian government on Monday for failing to immediately notify officials that its AI agents breached public services websites.…

    Connected by: OpenAIEARLIER COVERAGE
  3. Screenshot 2026 09 29 at 9.33.29 AM
    Meta Expands Its AI Agent Muse to Small Businesses With New Software Integrations

    Meta announced on Tuesday that it is expanding its artificial intelligence agent, Muse, to small businesses alongside new integrations with platforms such…

    Connected by: TuesdayEARLIER COVERAGE
  4. GettyImages 1822585391 1152x648 1
    OpenAI says planned GPT-6.1 is too insecure to release

    OpenAI has canceled the scheduled release of its updated GPT-6.1 model for next month due to safety regressions identified during testing. Initially…

    Connected by: OpenAIEARLIER COVERAGE
  5. NOW
    OpenAI Updates Codex With Reusable Cloud Development Environments and New CLI Voice CapabilitiesCURRENT UPDATE
A WireUnwired summary is already available. You can still write your own brief below for the reader community.
SOURCE & ATTRIBUTION
TechCrunch

Original author: Sarah Perez

Original publication: 29 September 2026 22:45

Read full story on TechCrunch ↗
RELATED STORIES
Editorial illustration for A Monster Water-Ice Cloud Keeps Repeating Over a Martian VolcanoNASA — Recently PublishedA Monster Water-Ice Cloud Keeps Repeating Over a Martian VolcanoEditorial illustration for OpenAI Streamlines ChatGPT Desktop App by Merging Chat and Work TabsTechCrunchOpenAI Streamlines ChatGPT Desktop App by Merging Chat and Work TabsEditorial illustration for Anthropic’s anti-cloning rules can't stop the AI game-copying boomArs TechnicaAnthropic’s anti-cloning rules can't stop the AI game-copying boom
Original sourceTechCrunch ↗