AI can mean many things: machine learning, large language models, generative AI and more. Here you'll find resources built for understanding how to effectively use AI in Chrome extensions.
Extensions enable you to enhance your browsing experience by controlling web content and customizing the browser. With AI you can take this to the next level.
  • Use AI to help create and comprehend content on the web.
  • Use the powerful extension APIs to enrich the bookmark experience, provide a better new tab page or make it easier to re-discover content from your browsing history.
  • Seamlessly embed your AI functionality into the browser via side panel, new-tab page, action bar or context menus.
You can build AI-powered extensions that summarize text, help with translation, generate content, assist with coding, provide recommendations, personalize user interfaces, and so much more. Check out how the Google Creative Lab team used AI and extensions to build an interactive creative coding experience.

AI-powered extensions in action

Check out the examples that demonstrate what's possible with Gemini in Chrome extensions.
Try out an extension that provides a chat interface for the Gemini API. Explore the code demonstrates how to use the Gemini Cloud API in a Chrome extension.
This extension provides a chat interface using the prompt API with Chrome's experimental built-in Gemini Nano model. Try out the extension and explore the code.
Try out an extension that summarizes the content of the currently open tab, built with the experimental Summarization API in Chrome.

How to integrate AI with extensions

On-device AI is the latest offering for bringing powerful models to users, while protecting sensitive data and improving latency. On-device cannot completely replace and replicate the work you do on the cloud, however, on-device can unlock great possibilities for your extensions such as ability to use purpose-built models, faster response times, offline availability and more.
Cloud AI offers a blend of power, scaleability and ease of integration. Cloud platforms provide access to cutting-edge hardware and software, ensuring high performance and continuous improvement through regular updates. The Gemini ecosystem brings together all Google's models, products and platforms.

Origin trials and early preview program

The Prompt API for Extensions is now available in an origin trial, so you can build Chrome Extensions that use Gemini Nano, our most efficient language model, in the browser.
We need your input to shape the APIs, ensure they fulfill your use cases, and inform our discussions with other browser vendors for standardization. Join our early preview program to provide feedback on early-stage built-in AI ideas, and discover opportunities to test in-progress APIs through local prototyping.

Best practices for AI-powered Chrome Extensions

For larger on-device models, trigger the download after the extension is installed. This way, you can manage the life cycle of your model independently of your extension and your users won't have to download the model with every extension update. Note that models are not considered remote hosted code.
Never share your keys with Chrome Web Store. Ask users to provide an API key. Proxy calls through your own server. Fetch the API key from your server before using it.
If you're using cloud AI APIs or otherwise sharing user input with a server, update your privacy policy to include what information is shared.
You're invited to reimagine the web with built-in AI. Create innovative web applications and Chrome Extensions, using Chrome's integrated AI models and APIs. Prizes total $65,000 USD.

Learn more about AI and extensions

Understand the basics and definitions of the various emerging technologies, often referred to as AI.
Learn how Chrome extensions work, what they can do, and how to build them.
Discover how AI can make it easier for developers to build powerful experiences on the web.