Browser maker Opera has introduced WebAI, a new web standard that enables users to run AI models directly in the browser without cloud connectivity, according to an announcement on October 27, 2026.
The standard is available as an early preview in Opera One and supports various open-weight AI models. Opera says WebAI works with Google’s Gemma, an open-weight model introduced in 2024, and supports Apple’s on-device foundation model on Macs. The company says the standard is not tied to specific models and is designed to accommodate a range of open-weight AI systems.
Users must opt into the feature. Opera plans to extend WebAI support to Opera GX, its browser for gamers and streamers, and Opera Neon, which uses AI agents for task automation.
According to Opera, WebAI allows users to generate text, classify content and analyze relationships between information directly in the browser. The company says developers can add AI features without operating AI infrastructure or paying per request, while users avoid AI subscription fees and keep data processed by local AI on their own devices.
Opera says the on-device processing approach addresses privacy concerns that have grown as AI assistants access more personal information. While locally run models do not eliminate all privacy risks, processing on users’ devices rather than company servers gives users more control over their data, the company says.
WebAI grew out of Opera’s previous work bringing locally run models into its browsers. Open-weight models are typically free to download and use, with publicly available model weights that give developers customization flexibility, though they come with some restrictions compared to fully open source software.