ChatGPT for Chrome Can Now Read and Use Your Open Tabs
OpenAI has upgraded its ChatGPT extension for Google Chrome so the assistant can read and reason over tabs you already have open The Verge. With the extension installed, you tag Chrome inside ChatGPT's web or desktop app to give it sight of those tabs.
OpenAI's example asks ChatGPT to compare sofas shown in three open tabs. The context comes directly from the pages named in the prompt.
The update also changes ChatGPT in the Chrome sidebar. It now offers full ChatGPT capability and full conversation history in Chat or Work, without leaving the page you are viewing The Verge. Work can operate Chrome tabs to send messages, fill out forms, or download files. The extension can also organize or group open tabs.
Beyond Chrome, documentation says the extension can work in an existing tab in Chrome, Edge, Brave, Opera, or Vivaldi, and is the path used when ChatGPT needs your regular browser profile OpenAI developer documentation. All five browsers support tab mentions and browser control from the ChatGPT desktop app OpenAI developer documentation. In the desktop app's built-in browser, you and ChatGPT see the same page, and ChatGPT can work across tabs and download files OpenAI help documentation.
This follows earlier browser steps. OpenAI previously offered a Chrome extension to search directly from the browser address bar OpenAI. In July 2025, Reuters reported that OpenAI planned to release a web browser to challenge Google Chrome Reuters, designed to keep some user actions inside a ChatGPT-like chat interface instead of clicking through to websites.
The broader context here is a shift from separate chat to assistance built into the browser. Tagging tabs replaces manual copying of links and text with live page context. Sidebar persistence means history and model capability travel as you move between pages. Profile reuse matters because logins and session state stay intact.
In my view, practitioners should watch the split between Chat and Work. Read access to tabs makes summarizing and comparing straightforward. Control that can send messages, submit forms, and fetch files raises questions about permissions and handling errors. For enterprise use, scoping is worth flagging. Tab grouping and explicit mentions offer a basic way to control what the model may see and touch. That control will need the same care as file permissions once assistants work routinely across many open pages. If that care is in place, comparison, triage, and form-heavy work get less tedious while users stay where the work already lives.
