OpenAI is shipping a significant update to Codex, transforming it into a more capable companion for the over 3 million developers who rely on it weekly to speed up work across the entire software development lifecycle.
Codex now has the ability to operate a user's computer alongside them, interact with more everyday tools and apps, generate images, recall user preferences, learn from past actions, and handle ongoing or repeatable tasks. The Codex desktop app also gains deeper support for developer workflows, including PR review, multi-file and multi-terminal views, SSH connections to remote devboxes, and a built-in browser for faster iteration on frontend designs, apps, and games.
Extending Codex Beyond Coding
With background computer use, Codex can now interact with all apps on a user's machine by seeing, clicking, and typing with its own cursor. Multiple agents can work on a Mac in parallel without disrupting the user's own activity in other applications. For developers, this is especially useful for iterating on frontend changes, testing apps, or working with tools that lack an API.
Codex is also beginning to work natively with the web. The app now includes a built-in browser where users can comment directly on pages to give precise instructions to the agent. This is currently useful for frontend and game development, and OpenAI plans to expand it so Codex can fully control the browser beyond localhost web applications.
Codex can now use gpt-image-1.5 to generate and refine images. Combined with screenshots and code, this is helpful for creating visuals for product concepts, frontend designs, mockups, and games within the same workflow.
OpenAI is also releasing more than 90 additional plugins that combine skills, app integrations, and MCP servers to give Codex more ways to gather context and take action across various tools. Notable new plugins for developers include Atlassian Rovo for JIRA management, CircleCI, CodeRabbit, GitLab Issues, Microsoft Suite, Neon by Databricks, Remotion, Render, and Superpowers.
Working Across the Software Development Lifecycle
The app now supports addressing GitHub review comments, running multiple terminal tabs, and connecting to remote devboxes over SSH (in alpha). Users can also open files directly in the sidebar with rich previews for PDFs, spreadsheets, slides, and docs, and use a new summary pane to track agent plans, sources, and artifacts.
Together, these improvements make it faster to move across all stages of the software development lifecycle-writing code, checking outputs, reviewing changes, and collaborating with the agent-all within a single workspace.
Carrying Work Forward Over Time
OpenAI has expanded automations to allow re-using existing conversation threads, preserving previously built-up context. Codex can now schedule future work for itself and wake up automatically to continue long-term tasks, potentially spanning days or weeks.
Teams use automations for everything from landing open pull requests to following up on tasks and staying on top of fast-moving conversations across tools like Slack, Gmail, and Notion.
OpenAI is also releasing a preview of memory, which allows Codex to remember useful context from prior experience, including personal preferences, corrections, and information that took time to gather. This helps future tasks complete faster and at a quality level previously only achievable through extensive custom instructions.
Codex now also proactively proposes useful work to continue where a user left off. Using context from projects, connected plugins, and memory, Codex can suggest how to start a work day or where to pick up on a previous project. For instance, Codex can identify open comments in Google Docs that need attention, pull relevant context from Slack, Notion, and the codebase, then present a prioritized list of actions.
Availability
These updates are rolling out starting today to Codex desktop app users signed in with ChatGPT.
Personalization features including context-aware suggestions and memory will roll out to Enterprise, Edu, and EU/UK users soon. Computer use is initially available on macOS and will also reach EU and UK users soon.
What's Next
In just the year since Codex launched, the ways developers use it have expanded significantly. Developers start with Codex to write code, then increasingly rely on it to understand systems, gather context, review work, debug issues, coordinate with teammates, and keep longer-running work moving forward.
OpenAI's mission is to ensure that AGI benefits all of humanity, which includes narrowing the gap between what people can imagine and what they can build. This release brings Codex closer to the tools, workflows, and decisions involved in building software, with much more planned for the near future.