Opera released a fresh web standard allowing people to execute artificial intelligence models right inside the browser, avoiding any need for cloud infrastructure.
Named WebAI, this capability supports multiple artificial intelligence models, including Google's open-weight Gemma model released two years ago, alongside Apple's on-device foundation model on Mac computers, according to the firm.
Opera stated that WebAI connects to various open-weight artificial intelligence systems rather than sticking to a single model, stemming from past efforts to integrate local models into its web browsers.
An early preview of these artificial intelligence tools is currently available in the flagship Opera One browser, while Opera GX and Opera Neon will receive the functionality soon, with users needing to opt in manually.
Open-weight models provide several advantages, such as free downloads and public model weights that grant developers greater customization freedom, though they still carry some restrictions compared to fully open-source software.
Privacy represents another benefit, as individuals can use artificial intelligence functions without transmitting personal details to corporate servers or purchasing cloud subscriptions.
"Developers can add AI features without running AI infrastructure or paying for every request," the company 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 also enables people to produce text, sort content, and analyze data relationships straight inside the browser.
As artificial intelligence assistants grow stronger and handle personal details, privacy worries increase because individuals often share large amounts of data to chatbots without knowing how it gets stored or used.
Running models locally provides an alternative since processing occurs on personal devices instead of cloud servers, giving users more control while aligning with Opera's history of emphasizing digital privacy.
Running artificial intelligence locally increases computer demands and can impact performance, with Opera pointing out that results rely entirely on device hardware.