One of the biggest additions is background computer use. Codex can now interact with apps on the user’s computer by seeing, clicking, and typing with its own cursor. The company says multiple agents can work in parallel on a Mac without interfering with the user’s activity in other apps. For developers, that makes Codex useful in scenarios such as iterating on frontend changes, testing applications, or working inside software that does not expose an API. The update also marks an early step toward native web use. Codex now includes an in-app browser that lets users comment directly on pages to give the agent more precise instructions. The current focus is on frontend and game development, while future plans aim to expand Codex’s ability to command the browser more broadly beyond localhost web applications.Codex for (almost) everything.
— OpenAI (@OpenAI) April 16, 2026
It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks. pic.twitter.com/UEEsYBDYfo
Codex is also gaining native image generation through gpt-image-1.5. The announcement says this will allow users to generate and iterate on visuals inside the same workflow they use for code and screenshots. That combination is presented as useful for product concepts, frontend design work, mockups, and games. At the same time, the release adds more than 90 new plugins. These combine skills, app integrations, and MCP servers to give Codex more ways to gather context and take action across tools. Among the plugins specifically highlighted for developers are Atlassian Rovo, CircleCI, CodeRabbit, GitLab Issues, Microsoft Suite, Neon by Databricks, Remotion, Render, and Superpowers.With computer use on macOS, Codex can now use any app by seeing, clicking, and typing with its own cursor.
— OpenAI (@OpenAI) April 16, 2026
It runs in the background without taking over your computer, working on tasks like frontend iteration, app testing, or any workflow that doesn't expose an API. pic.twitter.com/iO9iubLZX9
The app’s workflow layer is also being expanded. Codex now supports addressing GitHub review comments, running multiple terminal tabs, and, in alpha, connecting to remote devboxes over SSH. Files can now be opened directly in the sidebar with rich previews for PDFs, spreadsheets, slides, and documents. A new summary pane has also been added so users can follow agent plans, sources, and artifacts more easily. Together, the company says, these changes make it faster to move between writing code, checking outputs, reviewing changes, and collaborating with the agent inside one workspace instead of switching constantly across separate environments.You can now generate and iterate on images with gpt-image-1.5 in Codex to create frontend designs, mockups, game assets, and more without leaving your workflow.
— OpenAI (@OpenAI) April 16, 2026
Usage is included with your ChatGPT account, no API key needed. pic.twitter.com/ay17I3Nxoa
Another major theme in the update is continuity over time. Automations have been expanded so existing conversation threads can be reused, preserving previously built context. Codex can now schedule future work for itself and automatically resume long-running tasks over the course of days or even weeks. The announcement says teams are already using automations for work such as landing open pull requests, following up on tasks, and staying on top of fast-moving conversations across tools like Slack, Gmail, and Notion. A preview of memory is also being introduced, allowing Codex to retain useful context from previous experience, including personal preferences, corrections, and information that took time to gather. That, according to the release, helps future work finish faster and at a higher quality level than was previously possible without extensive custom instructions.Automations can now run in the same thread, so Codex can pick up where it left off, with the original context intact.
— OpenAI (@OpenAI) April 16, 2026
It can schedule future work and wake up automatically to continue long-term tasks, from landing open PRs to following up on tasks or staying on top of… pic.twitter.com/hzoWedPy3u
Codex is also starting to suggest useful next steps proactively. Using project context, connected plugins, and memory, the tool can now recommend how to start the workday or where to resume on an earlier project. One example in the announcement describes Codex identifying open comments in Google Docs, pulling relevant context from Slack, Notion, and the codebase, and then presenting a prioritized list of actions. Availability begins immediately for Codex desktop app users signed in with ChatGPT. Personalization features, including context-aware suggestions and memory, are set to roll out soon to Enterprise, Edu, and users in the EU and UK. Computer use is initially launching on macOS, with rollout to EU and UK users planned soon.We’ve also added support for 90+ plugins in Codex, giving it more ways to gather context and take action across the tools you already use for docs, project management, code review, creative work, deployments, and more. pic.twitter.com/IkmpDJwrLq
— OpenAI (@OpenAI) April 16, 2026