A Chrome extension to quickly ask ChatGPT about the page you're on
I made this tool for myself back in October after GPT-4 Vision came out. Being able to press Option+C, write a quick question, and hit Enter, with only the screenshot of the current tab as the context was a quick flow that I found very useful. I know there are most certainly more polished solutions out there now, but as we wait for the ChatGPT desktop app with builtin vision support I figured I'd release this now under an MIT license for whoever might find it useful. Plus this just automates your browser, meaning there's no need to put in API tokens or the like (you do have to be logged into…
In plain words
This Chrome extension lets users quickly ask ChatGPT questions about the current webpage by pressing a keyboard shortcut, typing a question, and sending it with a screenshot of the tab as context. Designed for anyone who wants fast access to ChatGPT's vision capabilities while browsing, it automates the browser without requiring API tokens—just an existing ChatGPT login. The tool is open-source under MIT license and available on GitHub, offering a lightweight alternative to more complex solutions.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I made this tool for myself back in October after GPT-4 Vision came out. Being able to press Option+C, write a quick question, and hit Enter, with only the screenshot of the current tab as the context was a quick flow that I found very useful. I know there are most certainly more polished solutions out there now, but as we wait for the ChatGPT desktop app with builtin vision support I figured I'd release this now under an MIT license for whoever might find it useful. Plus this just automates your browser, meaning there's no need to put in API tokens or the like (you do have to be logged into ChatGPT, however). I don't think I'll put it on the Chrome Web Store, so the installation steps are a bit annoying, but if even one person finds use in this, I'll be happy!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
