TensorFlow.js @TensorFlow__JS

Excited to share a project inspired by the #WebMCP Challenge! I've built an application that gives your agent control of your Android app using WebMCP. Yes, you heard it right—an Android app! 📱🚀

Instead of watching 1 hour of Netflix tonight, watch this ex-Google Chief Scientist Jeff Dean’s lecture. It’s the clearest explanation I’ve seen of the full AI engineering stack - from building LLMs from scratch all the way to one human coordinating 100 agents. The best part is that it’s useful whether you’ve never touched a model or you’ve been shipping agent systems every day for the past year. Bookmark it & watch the whole lecture this weekend, because it might end up being the most valuable thing you learn all week.

instead of watching 2 hours of Netflix tonight, watch this Stanford lecture given by Anthropic engineers it's the clearest explanation I've seen of how AI agents actually work useful whether you've never touched AI in your life or have been building with it every day i took the key ideas and turned them into a practical guide, with ready-to-copy prompts watch it, then read the guide below on how to build a system that improves itself

Anatoli Kopadze @AnatoliKopadze

2 months ago

x.com/i/article/2080…

94 537 4K 12.5M 16K

Web AI Monthly #33 (July edition) is now live: 🚀 The WebMCP revolution, 🤖 Embeddable front end assistants, and running local AI inside SaaS! linkedin.com/pulse/web-ai-m… Found mind-blowing #WebAI projects in the wild? Tag me to feature & build the #AI in #JS community together ❤️

LiteRT.js just landed from @Google. High performance #AI model inference right on the client side in browser. Everything runs locally - so total privacy and no token cost ✨ Learn more: developers.googleblog.com/litertjs-googl… #WebAI #EdgeAI #JS #webdev

Breaking news: Llama.cpp now supports #WebGPU which means you can now run any #gguf model in the web browser via #WebAI. One more Web AI runtime to add to your watchlist in addition to @Google's LiteRT-LM.js, WebLLM, and Onnx Runtime Web. Try it here: reeselevine.github.io/llamas-on-the-…

✨Recently took part in panel discussion with @AICollectiveCo in #SanFrancisco, and some deeper 1-1 interviews, with questions submitted by their community. Join us as we dive into the future of the agentic web, #WebAI, and of course #WebMCP!➡️ youtube.com/watch?v=jZyNql…

❓I can ask questions for what it sees to save time. This image shows it on my #LinkedIn profile to figure out best way to speak to that person - even got my MBTI personality correct!➡️ Everything runs entirely locally, so privacy when sharing pages that you may be signed into!

🤯I finally figured out how to get our client side #WebAI multimodal #Gemma 3N model to play nice in a #Chrome extension ✨ Now I can have a smart companion that can work with me in any tab I choose to share to it 🤖 I can even save examples that work well as "recipes" to reuse.

✨Wrote a #VectorDB layer on top of #IndexDB, to keep whole stack local. As it runs in browser on YOUR hardware it's private, costs zero dollars, and low latency. Powered by ⁠#webgpu for speed & builds upon 3 Web ML Libs: #TransformersJS #TFJS #LiteRT github.com/jasonmayes/Vec…

⭐️Give it a star on Github if you want me to keep evolving the code or have ideas: github.com/jasonmayes/Vec… ➡️Live demo to try for yourself right now: codepen.io/jasonmayes/liv…

Introducing VectorSearch.js (star it & I'll continue to work on it) - a #JS lib that allows you to perform semantic search over millions of vectors in ms, & can visualize embeddings too! Runs @Google's popular #EmbeddingGemma model entirely client side! github.com/jasonmayes/Vec…

Model update alert! Building on the Gemini 3 series, 3.1 Pro represents a step forward in core reasoning. Designed for tasks where a simple answer isn’t enough, it excels at workflows where the model must decide how to build the right solution. gemini.google.com/app

🚨 Demo Alert: Today I met with a really interesting company, bolt.new, who's involved in #WebContainers.🫙What's that? Imagine you could run Node.js in JavaScript on the client side via #Wasm.✨Time to combine with #WebAI right? Yeah I thought so too... #Offline

Woohoo! Client side #WebAI keeps getting better and better with #WebMCP. Thanks to @_philschmid for spreading the love ❤️

Philipp Schmid @_philschmid

8 months ago

MCP Servers Are Coming to the Web. MCP lets AI agents call tools on backends. WebMCP brings the same idea to the frontend, letting developers expose their website's functionality as structured tools using plain JavaScript (or even HTML), no separate server needed. Instead of

35 63 383 58K 323

Web AI Monthly #30: 2.5B downloads, ✨WebMCP, share GPUs for LLM inference, 🔎 vector search in browser for RAG , 🤖 Google's Gemma 3 270M in LiteRT.js linkedin.com/pulse/web-ai-m…

From PyTorch to the browser, simplified. LiteRT.js is a new #WebAI runtime designed to make it easier to run your custom .tflite models. See the demo from Matthew Soulanille and Chintan Parikh at the Web AI Summit → goo.gle/452pWm9

Want to build wealth but don’t know where to start? These 20 investing books created millionaires: 1. The Intelligent Investor – Benjamin Graham The bible of value investing. Warren Buffett calls it “by far the best investing book ever written.”

📚 Learn how to create stunning AI-powered web applications with Transformers.js, an innovative #JavaScript library for running state-of-the-art machine learning models 100% locally in your browser. ➡️ In this talk from my annual #WebAI summit @xenovacom , Open Source ML Engineer at Hugging Face, explores how to leverage emerging web technologies like #WebGPU and #WebNN to create interactive, privacy-preserving, and scalable web experiences. Watch now: youtube.com/watch?v=gJMiWw… #WebML #Transformers #JS #WebDev #AI #ClientSide

Why do so many cool AI demos fail to ship? Chrome's @KenjiBaheux calls it the "Playbook Vacuum." In his #WebAI summit talk, he isn't bringing a finished playbook—he's bringing a map and an invitation for the community to start writing it, together → goo.gle/3XWeHHC