Codex update features computer control, image generation, and enhanced developer workflows in OpenAI’s major release on April 16, 2026. The update expands the artificial intelligence coding assistant with new capabilities for more than 3 million weekly users who rely on Codex to accelerate work across the full software development lifecycle.
Codex Update Features Computer Control
Codex can now operate a user’s computer alongside them, seeing, clicking, and typing with its own cursor. Multiple agents can work on macOS in parallel without interfering with other applications. For developers, this capability proves useful when iterating on frontend changes, testing applications, or working in software that does not expose an API.
The update also includes an in-app browser where users can comment directly on web pages to provide precise instructions to the agent. This feature supports frontend and game development workflows, with plans to expand browser control beyond localhost applications in the future.
Image Generation and Plugin Expansion
Codex now integrates gpt-image-1.5 to generate and iterate on images. Combined with screenshots and code, this capability helps developers create visuals for product concepts, frontend designs, mockups, and games within the same workflow. The update also introduces more than 90 additional plugins that combine skills, app integrations, and MCP servers to expand Codex’s ability to gather context and take action across developer tools.
New plugins include integrations with Atlassian Rovo for JIRA management, CircleCI, CodeRabbit, GitLab Issues, Microsoft Suite, Neon by Databricks, Remotion, Render, and Superpowers. These additions extend Codex’s reach across the tools developers use daily.
Enhanced Developer Workflow Support
The Codex app now includes deeper support for developer workflows, including the ability to review pull requests, view multiple files and terminals simultaneously, and connect to remote development boxes via SSH in alpha. Users can open files directly in the sidebar with rich previews for PDFs, spreadsheets, slides, and documents.
A new summary pane tracks agent plans, sources, and artifacts, allowing developers to move faster across all stages of the software development lifecycle. This includes writing code, checking outputs, reviewing changes, and collaborating with the agent in one workspace.
Memory and Automation Capabilities
OpenAI expanded automations to allow reusing existing conversation threads and preserving previously built 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 these automations for 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 functionality allows Codex to remember useful context from previous experience, including personal preferences, corrections, and gathered information. This helps future tasks complete faster and to a quality level previously only possible through extensive custom instructions. Codex now proactively proposes useful work to continue where users have left off, using context from projects, connected plugins, and memory to suggest how to start work days or where to pick up on previous projects.
Rollout Timeline and Availability
The updates began rolling out immediately 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 and UK users soon. Computer use is initially available on macOS, with rollout to EU and UK users coming later.
Developers currently using Codex in the terminal or editor can now access it across their full workflow. Those new to Codex can download the app and begin using the expanded capabilities immediately. OpenAI stated that since Codex launched one year ago, developer usage patterns have expanded significantly, with users increasingly relying on the tool to understand systems, gather context, review work, debug issues, coordinate with teammates, and maintain longer-running projects.
