Opera One Brings On-Device AI Models and Interactive 3D Web Pages to Mac

Oct 27, 2026 688 views

Opera One is adding two browser capabilities with different ambitions: access to AI models running on a user’s device, and working web pages that can be placed inside 2D or 3D scenes. The WebAI feature is available as an opt-in preview starting today; Opera says its other browsers, Opera GX and Opera Neon, will follow.

Local AI through WebAI

WebAI is a proposed standard that would let websites and browser extensions call AI models hosted by the browser and run locally on a device. Opera’s implementation supports multiple model providers. At launch, users can access Google’s Gemma models and, on Macs, Apple’s on-device foundation model.

WebAI is a proposed web standard, backed by companies such as Google and Microsoft, that lets websites and browser extensions use AI hosted through the browser. Opera’s implementation is model-agnostic and built around open models, offering users choice among AI providers. At launch, users can already tap into models from Google and Apple, including Google’s Gemma and, on Macs, Apple’s on-device foundation model, directly in Opera.

The practical case is less about adding another chatbot and more about making AI available to browser tools without sending each request to a remote service. Opera says WebAI can generate text, classify content and find relationships between information. It’s optional, requires no subscription, and lets users choose which sites can access local models.

That setup could help developers add features without operating AI infrastructure or paying per request. Opera’s examples include extensions that organize tabs, flag clickbait or find relevant job postings. In those scenarios, the model handles information on the user’s device, with no account or fee required. Opera has published example extensions for exploring WebAI.

With local AI built into the browser, both users and developers can benefit from new capabilities. Local AI lets anyone build on top of free, open-weight AI models. Developers can add AI features without running AI infrastructure or paying for every request. Users don’t need AI subscriptions, the information the local AI handles stays on their own device, and they stay in control of the AI on their computer. For example, an extension could sort your tabs, flag clickbait or spot relevant job posts using a model on your laptop, with no account, no fee and no data sent to an AI service.

Web pages inside 2D and 3D scenes

Opera is also introducing HTML-in-Canvas, which lets developers place functional web pages inside 2D and 3D environments. Pages can retain interactive elements such as menus, buttons and forms as they move through a scene, and developers can build them with HTML and CSS.

Maciej Kocemba, Product Director at Opera GX, described the feature as a way to put a real web page into a 3D world while keeping its controls and content usable. Opera wants users to try the technology early and see what they build.

“Honestly, this is a fun one […]. You can take a real web page and throw it into a 3D world, and everything still works: buttons, text, menus, all of it. We wanted users to get their hands on it early and see what they come up with.”

Opera’s demonstrations include Webpage Bulldozer, which turns page elements into physical objects, and Gamer Room, a virtual 3D space with screens showing live web pages. Both run in Opera browsers without additional setup; Opera has posted the demos here.

WebAI tests whether the browser can serve as a controlled bridge between local models and web software. HTML-in-Canvas explores a different boundary, bringing standard interactive pages into spatial experiences. Together, the previews point to Opera’s broader effort to make the browser an active platform for both local computing and new forms of web interaction.

Source: Marcus Mendes · 9to5mac.com

Comments

Sign in to comment.
No comments yet. Be the first to comment.

Related Articles

Opera One now lets Mac users run Apple’s foundation model...