As much as I struggle with on-device processing and the quality of its output compared to server models, I am excited by some of the APIs that are being built into browsers that are backed by LLMs and other AI inference models. For example, the prompt API, along with a multi-modal version that can take any arbitrary combination of text, image, and audio and run prompts against them. These APIs are neat but not yet web-exposed and many developers struggle to know what to do with a generic prompt. It’s not a solution that is natural to many people yet.
Browser AI API for Utilizing On-Device Models · Issue #178 · WICG/proposals
Introduction The Browser AI API is a proposal for a new browser feature that makes AI models accessible directly on users' devices through the browser. By offering a simple API available on the...
3W for In-Browser AI: WebLLM + WASM + WebWorkers
What if AI agents could run entirely in your browser? Not just the UI part—the actual model inference, agent logic, and response generation, all happening locally without a single API call.
Stop Ignoring the Browser: The Biggest Frontend Shift in a Decade
Native browser APIs now provide powerful alternatives for routing, state management, and components. Never mind the frameworks, use the browser.
BrowserOS - Open-Source AI Browser
The open-source browser with AI superpowers. Privacy-first Chrome alternative backed by Y Combinator.
Browser Use - The way AI uses the internet
78,000+ GitHub stars. Trusted by Fortune 500. The #1 open-source browser automation platform.
AI browsing now available for early testing in Brave | Brave
Today, we're announcing the availability of Brave's new AI browsing feature for early testing. This agentic experience aims to turn the browser into a truly smart partner, automating tasks and helping people accomplish more.
Running inference in web extensions | The Mozilla Blog
Image generated by DALL*E We’re shipping a new API in Firefox Nightly that will let you use our Firefox AI runtime to run offline machine learning tasks
Wasm-agents: AI agents running in your browser
One of the main barriers to a wider adoption of open-source agents is the dependency on extra tools and frameworks that need to be installed before the agents can be run. In this post, we show how to write agents as HTML files, which can just be opened and run in a browser.
browser-use/browser-use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Built-in AI | AI on Chrome | Chrome for Developers
Chrome looks set to ship an LLM Prompt API to the web platform. At Mozilla, we oppose this API. We feel it has a large interoperability risk, and Google imposing T&Cs on a web API sets a dangerous precedent. Full details: github.com/mozilla/standards-positions/i…
Prompt API · Issue #1213 · mozilla/standards-positions
github.com
