Opera has announced a new web standard called WebAI that enables local execution of AI models within its browser. The company says WebAI is not tied to any single model and is designed to support a wide range of open-weight AI systems. On Macs, it also works with Apple's on-device foundation model.
The feature is currently available as an early preview in Opera One, with plans to bring it to Opera GX, the company's browser for gamers, and Opera Neon, which uses AI agents. Users must opt in to activate the feature.
Opera highlights several advantages of running models locally. Open-weight models are generally free to download and use, and their publicly available weights give developers more flexibility to customize them. Privacy is a key benefit, the company says: processing happens on the user's own device, so personal information is not sent to remote servers or tied to a subscription.
"Developers can add AI features without running AI infrastructure or paying for every request," Opera said in its announcement. "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."
WebAI can also generate text, classify content, and identify relationships between pieces of information directly in the browser. The company notes that model performance depends on the device's hardware, meaning users with less powerful computers may see slower results.