#WebAI Lib for semantic vector search, search millions of vectors in milliseconds, and visualize the tokens or embeddings too! Runs entirely client side in web browser (custom Vector DB written on top of IndexDB) Supports EmbeddingGemma & all-Mini-L6-v2!⭐️https://github.com/jasonmayes/VectorSearch.js

🤯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.

Building an article assistant: local AI in the browser with cloud fallback - Richard MacManus How I built an article assistant for my website that uses local AI (via Chrome + Gemini Nano) when available, and falls back to a cloud model when it isn’t.

New from my Web AI Lab: I’ve built an “article assistant” for my site that runs using local AI in the browser (via Chrome + Gemini Nano) when available — and falls back to a cloud model when it isn’t.

I think local AI has huge implications for the #OpenWeb.

ricmac.org/2026/03/19/a... #WebAI

Original post on mastodon.social

New from my Web AI Lab: I’ve built an “article assistant” for my site that runs using local AI in the browser (via Chrome + Gemini Nano) when available — and falls back to a cloud model when it isn’t.

Before you dismiss this because it's AI, I think this has huge implications for the #OpenWeb […]

Innovative Partnership Between webAI and Qwake Enhances Fireground Predictive Intelligence webAI collaborates with Qwake Technologies to leverage predictive AI capabilities aimed at enhancing emergency response in fire departments, focusing on real-time data usage.

Innovative Partnership Between webAI and Qwake Enhances Fireground Predictive Intelligence #USA #Austin #webAI #Predictive_AI #Qwake_Technologies

Screenshot of a blog post on Joan León’s website titled “Adding an AI summary to blog posts with the Chrome Summarizer API.” The page shows a button labeled “AI Summary” and a highlighted summary box containing bullet points that explain how the Chrome Summarizer API works, including local summarization with Gemini Nano, browser requirements, streaming summaries, and implementation details. The site navigation and language selector are visible at the top.

Chrome is bringing AI directly into the browser with the Summarizer API.

In this post I show how to add an AI-generated summary to blog posts using the Chrome Summarizer API and models running locally in the browser.

No external APIs. No token costs.

#AI #WebAI #JavaScript #Chrome

webAI and Qwake Technologies Join Forces for AI-Driven Emergency Response Solutions webAI has partnered with Qwake Technologies to enhance emergency response through predictive AI, revolutionizing fire department operations nationwide.

webAI and Qwake Technologies Join Forces for AI-Driven Emergency Response Solutions #United_States #Austin #AI_Technology #webAI #Qwake

Original post on mastodon.social

I experimented with WebMCP on my personal website, exposing two tools an AI assistant can call directly from the browser: searching an article and subscribing to my newsletter. It’s a small prototype, but it hints at how websites are fast becoming AI-interactive surfaces […]

Utter - Chrome Web Store Global hotkey for voice-to-text input using Speech Recognition

In enterprise environments, cloud-based STT is often a non-starter.

@paul.kinlan.me 's "Utter" Chrome extension fixes this with the WebSpeech and Prompt APIs to transcribe and polish your "train of thought" entirely on-device.

chromewebstore.google.com/detail/utter...

#WebAI #BuiltInAI

Original post on mastodon.social

As part of my #WebAI explorations, I've built an AI chatbot for my personal website called Ask Ricmac. Under the hood, it runs on a Cloudflare Workers backend that uses Vectorize, D1 and Workers AI. During development, I also used the WordPress MCP Adapter and Claude Desktop. In this post I […]

webAI Joins Forces with U.S. Army for Project ARIA to Enhance AI Capabilities webAI has been chosen as an industry partner for the U.S. Army's Project ARIA, focusing on delivering advanced AI tools, enhancing operational efficiency.

webAI Joins Forces with U.S. Army for Project ARIA to Enhance AI Capabilities #United_States #Washington #U.S._Army #webAI #Project_ARIA

Baked an on-device visual narrator by running Qwen3.5-0.8B on WebGPU 🤓

It can describe, analyze, or extract text from any pasted or uploaded image, all without your data ever leaving your machine.

Try it 👇

h3manth.com/ai/visual-na...

#AI #WebAI #LLM

Becoming a Web AI Practitioner: A Map of the Emerging Stack - Richard MacManus Earlier this month, I was laid off from my job as senior editor at The New Stack. While I figure out what’s next, I resolved to dive into a technology stack I’ve been deeply interested in for a while: Web AI. Only this time not just writing about these technologies,…

While I figure out what’s next in my career, I resolved to dive into a technology stack I’ve been deeply interested in for a while: Web AI. Only this time not just writing about these technologies, but building apps with them too. ricmac.org/2026/02/26/w... #WebAI

Original post on mastodon.social

While I figure out what’s next in my career, I resolved to dive into a technology stack I’ve been deeply interested in for a while: Web AI. Only this time not just writing about these technologies, but building apps with them too. In this post, I’ve taken a stab at a high-level overview of the […]

We’re close to a future where we don't manually write docs 💻

Catching up on tools since returning to work and tried Code Wiki on the React repo. It generates docs staying in sync with the code.

It’s a pretty cool enabler for open source contributions. Have you tried this?

#WebDev #ReactJS #WebAI

Inside the Web AI Revolution: On-Device ML, WebGPU, and Real-World Deployments Client-Side AI Systems: Integrating WebGPU, ONNX, MediaPipe, and Built-In Browser Models

Inside the Web AI Revolution: On-Device ML, WebGPU, and Real-World Deployments #webai #webgpu #webassembly #onnx #llm #mediapipe senoritadeveloper.medium.com/inside-the-w...

Everything to make this self generating code execution demo work is running client side in a web browser using #WebContainers + #WebAI. Total privacy, sandboxed code execution (Node.js via Wasm), zero cost. Using off the shelf 2B Gemma model (not tuned) 69pjnq.csb.app

WebMCP Bridge Bridge any remote MCP server to Chrome's WebMCP API. Discover tools, prompts, and resources — then let browser AI agents use them.

Built webmcp-bridge to map remote MCP tools into WebMCP in the browser.

Connect MCP server -> discover tools -> register with navigator.modelContext.provideContext() -> invoke from browser AI (Prompt API) surfaces.

h3manth.com/ai/webmcp/

#WebMCP #MCP #PromptAPI #WebAI #JavaScript

🚨 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... Try it: 69pjnq.csb.app

🎖️ Thrilled to announce Google extended my #GDE membership for another year! It's been an incredible journey since 2019 in Web Technologies (AI for Web Developers, Progressive Web Apps, #ProjectFugu) & Angular. Let's continue to push the boundaries of the Web together! 🚀 #WebAI #Angular #PWA

Offline vector search with SQLite and EmbeddingGemma

Build an offline RAG system that runs entirely in the browser. In his #WebAI Summit talk, Google DevRel Engineer @rodydavis.com shows you how to use SQLite and EmbeddingGemma to get it done → goo.gle/4qBb8ne

webAI Appoints Dr. Paul J. Maykish as Chief Intelligence Officer, Launches Intelligence Lab webAI has appointed Dr. Paul J. Maykish as Chief Intelligence Officer. The newly launched Intelligence Lab aims to develop accessible, sovereign AI for real-world applications.

webAI Appoints Dr. Paul J. Maykish as Chief Intelligence Officer, Launches Intelligence Lab #USA #Austin #webAI #Intelligence_Lab #Paul_J._Maykish

webAI Announces Appointment of Paul J. Maykish as Chief Intelligence Officer webAI has appointed Dr. Paul J. Maykish as its Chief Intelligence Officer and launched the webAI Intelligence Lab to implement impactful AI systems.

webAI Announces Appointment of Paul J. Maykish as Chief Intelligence Officer #USA #Austin #AI_Lab #webAI #Paul_J._Maykish

webAI Appoints Dr. Paul J. Maykish as Chief Intelligence Officer and Opens New Lab webAI has appointed Dr. Paul J. Maykish as Chief Intelligence Officer and launched the webAI Intelligence Lab, focused on advancing accessible AI technology.

webAI Appoints Dr. Paul J. Maykish as Chief Intelligence Officer and Opens New Lab #USA #Austin #webAI #Intelligence_Lab #Paul_J._Maykish

webAI Welcomes Dr. Paul J. Maykish as Chief Intelligence Officer and Unveils new Intelligence Lab webAI has appointed Dr. Paul J. Maykish as Chief Intelligence Officer and launched the webAI Intelligence Lab to promote accessible and sovereign intelligence.

webAI Welcomes Dr. Paul J. Maykish as Chief Intelligence Officer and Unveils new Intelligence Lab #USA #Austin #webAI #Dr._Paul_J._Maykish #Intelligence_Lab

Generative AI | 2025 | The Web Almanac by HTTP Archive Generative AI chapter of the 2025 Web Almanac covering the transition to local browser-based AI, the adoption of WebNN and Built-in AI, new discoverability standards like llms.txt, and the emergence o...

The wait is over! The @httparchive.org has officially released the 2025 Web Almanac. 🚀 I led the new #GenerativeAI chapter, which "delves" ;) into the hard numbers of AI adoption on the web, backed by data from millions of sites.

➡️ almanac.httparchive.org/en/2025/gene...

#theWebAlmanac #WebAI

Mind-controlled drones with Web AI & TensorFlow

What does the future of human-machine collaboration look like? It might be mind-controlled drones. In her #WebAI summit talk, Dara Tumenbayeva showcases this technology and its applications in e-sports and robotics → goo.gle/3ZiwSrG

Web AI: Client Side Machine Learning

Run Google's powerful Gemma 3 and 3n LLMs directly in the browser. In this #WebAI summit talk, MediaPipe Web Creator Tyler Mullen covers how it's possible with just a few lines of code → goo.gle/4qONyTB

Web AI: Client Side Machine Learning

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

@tomayac.com Android is a bit kneecapped for #webAI in a way that iOS isn't.

Any idea why Android devices are limited to 30fps on getUserMedia() camera access on front cameras?
Native apps on Android can get 60fps.

iOS web can get 60 on front cams. Tested on several phones

/cc @webai.bsky.social