We need to talk more The web is much more than browsers. What works great in browser development is missing in related spaces like embedding. Can we get together to collectively describe security and compatibility properties of user agents that are not browsers? Can we develop things that don’t ...
Group Note Draft: Web User Agents
Web user agents include both web browsers and other intermediaries between end-users and the web.
one-agent-one-browser/src/dom.rs at 0.1.0 · embedding-shapes/one-agent-one-browser
One from scratch browser built by one human and one agent, working hand in hand - embedding-shapes/one-agent-one-browser
Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet | Brave
The attack we developed shows that traditional Web security assumptions don't hold for agentic AI, and that we need new security and privacy architectures for agentic browsing.
one-agent-one-browser/src/platform/x11/mod.rs at 0.1.0 · embedding-shapes/one-agent-one-browser
One from scratch browser built by one human and one agent, working hand in hand - embedding-shapes/one-agent-one-browser
How might a browser be developed?
There’s a confluence of things that have happened recently that have made me question how browsers might be developed: On January 8th 2026, Simon Willison predicted that someone will build a browser using mainly AI-assisted tools within 3 years On January 27th 2026, one human and one agent built a browser from scratch (great experiments) On the 19th February 2026, news came out that Taalas had a chip that can spit out nearly 17,000 tokens per second by baking a model onto the chip. I would like to indulge in a little bit of projection and in my case, some science fiction of my own.
User Agency in Other People's Websites - Orion Reed at JOTB25
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.
Anchor - Secure Infrastructure for Computer Use Agents
Secure Infrastructure for Computer Using AI agents - Deploy millions of browser agents to automate any web task. Faster, cheaper, and more reliable than human operations.
Launch HN: Browser Use (YC W25) – open-source web agents | Hacker News
Check out this video to see it in action: https://preview.screen.studio/share/r1h4DuAk. There are lots more demos at https://github.com/browser-use/browser-use on how we control the web with prompts.
elements
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.
You're Gonna Need A Bigger Browser
Browsers are hugely load-bearing in the Web's architecture, and yet they haven't changed very much in quite a while. If the Web is indeed for user agency, we should take a hard look at our user agents to see if they might not need improvement.
Opera unveils an AI agent that runs natively within the browser | TechCrunch
Browser company Opera has unveiled a new AI agent called Browser Operator that can complete tasks for you on different websites. In a demo video, the
2025 Chromium Embedding: Experiences and challenges
Web Engines Hackfest. Contribute to Igalia/webengineshackfest development by creating an account on GitHub.
Meet Opera’s AI Browser Operator
We're introducing an AI agent into the browser making us the first major browser with AI-based agentic browsing.
