88Z AI, 8 May — OpenAI has officially launched the Codex Chrome extension, enabling Codex to directly operate within a user's logged-in Chrome browser. The plugin supports reading tabs, page content, and login information, while performing interactions like navigation, clicking, typing, and screenshots. Users retain full control, with the ability to stop tasks, manage permissions, and confirm interactions with new websites.
At a glance
- The Codex extension supports reading browser content and performing interactions like clicking and typing
- Users can stop tasks anytime and must confirm interactions with new websites for security
The update
OpenAI has officially released the Codex Chrome extension, designed to allow Codex to directly operate within the user's currently logged-in Chrome browser environment. Through this plugin, Codex can read open tabs, specific page content, and information from logged-in websites. It also supports various interactive operations, including page navigation, element clicking, text input, and screen capturing. Regarding security and control, users maintain a high degree of autonomy. They can stop ongoing tasks at any time and flexibly manage access permissions in the settings. To ensure safety, the system requires user confirmation before Codex interacts with new websites, thereby guaranteeing user awareness and control over browser operations.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- OpenAISource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.