OpenAI Brings Native Web Access, Personalization Tools to Codex in Latest Upgrade
In Focus
- The upgrade introduced image generation and computer-use features to Codex
- The update expands Codex’s use cases among developers and enterprises
- The new AI features will initially be available on macOS
OpenAI has updated Codex with new AI features, including image generation, computer use, native access via web, and personalization tools. OpenAI’s new Codex features improve the usability of the coding platform significantly. Initially, the new features will be available on macOS. The company plans to introduce the Codex enterprise features on Windows in the coming weeks.
New Codex Features Expand Its Use Case
OpenAI’s latest Codex update is expected to expand its use case among enterprises and developers. The company said the update enables the platform to run computers and integrate with different tools and applications.
Using AI agents, the coding platform can process content displayed on the screen, enter text in documents and text boxes, and click on icons. The feature is designed to work in the background, allowing users to either monitor the platform or continue with other tasks.
“Codex can now operate your computer alongside you, work with more of the tools and apps you use everyday, generate images, remember your preferences, learn from previous actions, and take on ongoing and repeatable work. The Codex app also now includes deeper support for developer workflows, like reviewing PRs, viewing multiple files, and terminals, connecting to remote devboxes via SSH, and an in-app browser to make it faster to iterate on frontend designs, apps, and games,” OpenAI noted in its statement.
OpenAI updated its coding platform weeks after it launched Codex on the Windows platform. The move widened access to programmers and software engineers who use the Windows operating system.
Latest Upgrade Allows Codex to Access the Web
OpenAI’s latest Codex upgrade allows the coding platform to work with the web through an in-app browser. The Codex web access feature allows users to instruct AI agents by commenting directly on pages.
The AI developer said this feature only works with web applications that can be accessed locally. Additionally, OpenAI’s upgrade brought new image generation capabilities to Codex.
With these capabilities, Codex can create and edit images using the GPT-image-1.5 AI model. The ChatGPT maker says the image-generation feature will enable users to create visuals for mockups, product concepts, games, and frontend designs.
The AI developer added that developers who use Codex to complete, test, and iterate on frontend coding tasks will find the feature to be useful. While unveiling the new features, OpenAI said that over three million developers use the Codex every week.
OpenAI Introduced New Plugins to Codex
OpenAI also released over 90 plugins to enable Codex to work with other agentic platforms to further expand the platform’s use cases. These platforms include Atlassian Rovo, CodeRabbit, Circleci, Microsoft Suite, Render, GitLab Issues, and Superpowers. The AI lab released new AI features on Codex on the same day when Anthropic launched Claude Opus 4.7. This update introduces new improvements to software engineering.
