Opera Introduces WebAI Standard to Run AI Models Locally in the Browser

Browser maker Opera has introduced WebAI, a new web standard that allows users to run AI models directly within its browser rather than relying on the cloud. The standard is designed to work with a wide range of open-weight models, including Google’s Gemma, and supports Apple’s on-device foundation model on Macs. It builds on Opera’s earlier efforts to bring locally run models to its browsers.

WebAI is available as an opt-in early preview in the flagship Opera One browser, with Opera GX, aimed at gamers and streamers, and the agent-driven Opera Neon set to follow soon. The company said the standard lets anyone generate text, classify content and understand relationships between pieces of information directly in the browser.

Opera said developers can add AI features without running their own infrastructure or paying per request, while users avoid AI subscriptions, keep data on their own devices and retain control over the AI on their computers. Open-weight models are typically free to download and allow greater customization, though they carry some restrictions compared with fully open source software.

The move reflects growing privacy concerns as AI assistants gain access to personal information. However, running models locally places greater demands on hardware, and Opera noted that performance will depend on each user’s device.