6 Sources
[1]
Opera introduces a new web standard to let users deploy AI locally in their browser
Browser maker Opera has introduced a new web standard that lets users to run AI models directly in its browser, without relying on the cloud. The new standard, WebAI, is designed to work with a variety of AI models. Opera name drops Google's Gemma -- an open-weight model that Google first
[2]
Opera will run AI locally in your browser now - why that's a gamechanger and how to try it - ZDNET
Thanks to the newly proposed WebAI web standard, the company will start shipping local AI models with its flagship browser. * Opera is releasing an important AI feature. * Local AI is now getting built right into the web browser. * There'll be no need to configure or install the likes of
[3]
Opera One now lets Mac users run Apple's AI model directly in the browser
Starting today, Opera One users can access a preview feature that lets them tap into local AI models through WebAI, a proposed web standard. Here are the details. WebAI Opera announced today that its Opera One browser is the first of its browsers to offer built-in access to local AI models, with
[4]
Opera wants websites to run AI on your laptop instead of sending your data to the cloud
The opt-in WebAI preview is rolling out to Opera One on supported Windows PCs and Apple silicon Macs, with no separate AI account or subscription required Opera wants to move routine AI work out of distant data centers and onto the computer already sitting on your desk. Its new WebAI preview lets
[5]
Opera WebAI Lets Users Run Local Browser AI Without Cloud Servers
Opera recently announced that it's bringing "local" artificial intelligence directly into its browsers through WebAI, which is now in early preview across Opera One, Opera GX, and Opera Neon. Opera says that WebAI is entirely opt-in and lets users choose from multiple compatible local models. That
[6]
You can now drop working webpages into 3D rooms with Opera's latest update
* Opera runs local open-weight AI (Gemini, Apple Silicon) in desktop browsers -- on-device, no cloud, no subscriptions. * Playground has 8 on-device APIs: Prompt, Summarizer, Writer, Rewriter, Translator, Proofreader, Embedder, Decisions. * HTML-in-Canvas lets you drop live web pages into 2D/3D
Share
Copy Link
Opera launches WebAI, a new web standard that enables local AI processing directly in browsers. The opt-in feature supports open-weight AI models including Google's Gemma and Apple's on-device foundation model, eliminating the need for cloud services or AI subscriptions while keeping user data on their devices.
Opera has introduced WebAI, a new web standard that allows users to run AI models locally within their browsers, marking a significant shift away from cloud-based AI processing
1
. The feature is now available as an early preview in the Opera One browser, with Opera GX and Opera Neon set to receive the same capabilities soon1
.
Source: ZDNet
Opera WebAI addresses growing privacy concerns by keeping AI processing entirely on users' devices rather than sending data to external servers. "A lot of what people want from AI doesn't need a data center. Your laptop can already do it, without sending your data anywhere," said Krystian Kolondra, EVP Browsers and AI at Opera
2
. This privacy-focused alternative to cloud AI means users can access AI features without surrendering personal information to company servers or paying for cloud-based AI subscriptions1
.The new web standard is model-agnostic and built around open-weight AI models, giving users choice among AI providers
3
. At launch, users can tap into Google's Gemma and, on Apple silicon Macs, Apple's on-device foundation model directly in Opera3
. Opera emphasizes that WebAI isn't tied to any particular model and is designed to support a wide range of open-weight AI systems1
.
Source: 9to5Mac
WebAI opens local AI processing to third-party developers instead of reserving it exclusively for Opera's features
4
. Developers can add AI features without running expensive AI infrastructure or paying for every request, enabling more innovation for the Opera One browser2
. The feature supports Prompt, Decision, and Semantic Embeddings APIs5
.Opera has kept WebAI as an opt-in feature, ensuring nothing is downloaded until users enable it
4
. Each website needs permission before accessing the browser's local AI, adding an extra layer of user control when websites can call models running on the computer4
. Users can enable the feature by updating Opera One, going to Settings > Opera AI, and turning on Enable Web AI API2
.Opera released six experimental extensions demonstrating WebAI's capabilities, including "Project Lens" for context-based article highlighting, "Got It?" for reading comprehension quizzes, and "Questionable Intelligence" for chart-based data analysis
5
. Other examples include extensions that can sort messy tab collections and flag clickbait content4
. WebAI can generate text, classify content, and identify relationships between pieces of information directly in the browser3
.
Source: TechCrunch
Related Stories
The early preview is currently available on 64-bit Windows PCs with Intel or AMD processors and Apple silicon Macs, excluding Intel-based Macs, Linux, and Windows on Arm
5
. Running AI models locally places greater hardware demands on users' computers, which can affect performance1
. Opera notes that model performance depends on the device's hardware, though the company hasn't disclosed minimum performance requirements4
.WebAI is a proposed web standard backed by companies including Google and Microsoft
3
. Opera first shipped local models to developers in 2024 and is now bringing them to all users, with more models and tools coming2
. Additionally, Opera launched HTML-in-Canvas, which lets developers embed fully functional web pages into 2D and 3D environments with interactive elements remaining usable3
. This move positions Opera as a champion of local AI, making browser-based AI processing easier than previous solutions that required separate installations like Ollama2
.Summarized by
Navi
[2]
[4]
02 Dec 2025•Technology

03 Mar 2025•Technology

16 Apr 2026•Technology
