Opera launches webai standard for local AI execution in browsers

Opera has launched a new web standard called WebAI, enabling users to run AI models directly in their browser without relying on cloud infrastructure. The standard supports various AI models, including Google’s Gemma and Apple’s on-device foundation model on Macs. WebAI is designed to be model-agnostic, supporting a wide range of open-weight AI systems. The feature is currently available in Opera One as an early preview and will soon be rolled out to Opera GX and Opera Neon. Users must opt-in to access the feature. Open-weight models offer benefits such as free access, public model weights, and enhanced privacy, as users can leverage AI features without sending personal data to servers. Opera highlights that developers can integrate AI without running infrastructure or paying for each request, while users retain control over their data. WebAI allows text generation, content classification, and information analysis directly in the browser. Privacy concerns have grown with AI assistants gaining access to personal data, making local model execution an attractive alternative. However, running AI models locally can strain device hardware, with performance depending on the device’s specifications. Opera emphasizes its commitment to digital privacy, a key selling point in its long-term strategy.