OpenAI announced an update to Codex that the company says adds background computer use, native browser integration, image generation via gpt-image-1.5, persistent memory, and more than 90 additional plugins. OpenAI states the update is rolling out starting today to Codex desktop app users signed in with ChatGPT.
OpenAI says Codex is used weekly by more than 3 million developers, and frames the release as an expansion of the agent across what it calls the full software development lifecycle. The company describes the update as bringing Codex "closer to the tools, workflows, and decisions involved in building software."
Computer Use and In-App Browser
According to OpenAI, Codex can now "operate your computer alongside you" by seeing, clicking, and typing with its own cursor. The company says multiple agents can run in parallel on a Mac without interfering with the user's work in other applications, and cites frontend iteration, app testing, and working with apps that lack APIs as intended use cases.
OpenAI says the Codex app also includes an in-app browser where users can comment directly on pages to give the agent instructions. The company describes the current browser integration as useful for frontend and game development, and states it plans to expand Codex to "fully command the browser beyond web applications on localhost."
Computer use is initially available on macOS, per OpenAI, and the company says it will roll out to EU and UK users at an unspecified later date.
Image Generation via gpt-image-1.5
OpenAI says Codex can now use gpt-image-1.5 to generate and iterate on images. The company states that, combined with screenshots and code, the model is useful for "creating visuals for product concepts, frontend designs, mockups, and games inside the same workflow." OpenAI did not publish benchmark data for the model in this announcement.
More Than 90 New Plugins
OpenAI says it is releasing more than 90 additional plugins that combine skills, app integrations, and MCP servers. The company highlights several integrations it expects developers to find useful, including Atlassian Rovo to help manage JIRA, CircleCI, CodeRabbit, GitLab Issues, Microsoft Suite, Neon by Databricks, Remotion, Render, and Superpowers.
Codex can now schedule future work for itself and wake up automatically to continue on a long-term task, potentially across days or weeks.
That description comes from OpenAI's announcement, which says expanded automations can reuse existing conversation threads to preserve prior context. The company says teams use automations for tasks such as landing open pull requests, following up on work items, and tracking conversations across Slack, Gmail, and Notion.
Memory and Proactive Suggestions
OpenAI is releasing what it calls a preview of memory, which the company says allows Codex to remember context from previous sessions, including personal preferences, corrections, and information that "took time to gather." OpenAI states that this is intended to reduce the need for extensive custom instructions.
The company also says Codex can now proactively propose work based on context from projects, connected plugins, and memory. As an example, OpenAI states that Codex can identify open comments in Google Docs that require attention, pull related context from Slack, Notion, and the user's codebase, and produce a prioritized list of actions.
OpenAI says personalization features, including context-aware suggestions and memory, will roll out to Enterprise, Edu, and EU and UK users "soon," without providing a specific date.
Developer Workflow Additions
According to OpenAI, the Codex app now supports addressing GitHub review comments, running multiple terminal tabs, and connecting to remote devboxes over SSH in alpha. The company says the app also lets users open files directly in the sidebar with rich previews for PDFs, spreadsheets, slides, and documents, and includes a new summary pane for tracking agent plans, sources, and artifacts.
OpenAI describes the combined changes as making it faster to move between writing code, checking outputs, reviewing changes, and collaborating with the agent in a single workspace.
Pricing and Availability
OpenAI's announcement (https://openai.com/index/codex-for-almost-everything) does not include standalone pricing for the updated Codex app or the new plugins, and states only that access requires signing in with ChatGPT. The company did not specify which ChatGPT subscription tiers are required for individual features such as computer use, memory, or the gpt-image-1.5 integration. DeepBrief has not independently verified the rollout timeline, the plugin list, or the capability claims described by OpenAI.
On the mission framing, OpenAI wrote: "Our mission is to ensure that AGI benefits all of humanity. That includes narrowing the gap between what people can imagine and what they can build."