Opera has introduced WebAI, a new web standard that lets users run AI models directly in the browser instead of sending requests to the cloud.
The standard is designed to support a range of open-weight models, including Google’s Gemma. On Mac computers, it also supports Apple’s on-device foundation model, according to Opera. The company said WebAI is not tied to a specific model and builds on its earlier work with locally run AI.
Opera is offering the feature as an opt-in early preview in Opera One. Opera GX, its browser for gamers and streamers, and Opera Neon, its AI-agent browser, are expected to receive the feature soon.
WebAI can support tasks such as text generation, content classification and identifying relationships between pieces of information. Because processing takes place on the user’s device, Opera said developers can add AI features without operating AI infrastructure, while users can avoid cloud subscriptions and keep handled data on their computers.
Local AI also comes with trade-offs. Running models on-device can place greater demands on hardware, and Opera said performance will vary depending on the user’s computer.
Source: TechCrunch
