GDGHK AI Session: On-Device Intelligence & Agentic Web (With AI: Edge Computing and the New Era of Agentic Web)

Description

Join GDG Hong Kong for an intensive session focused on Web AI Agents and Edge Computing. We are honoured to welcome Jason Mayes, Google's Web AI Lead, along with local GDEs. We will explore how to build AI applications that are completely offline, privacy-friendly, and entirely free in terms of hosting costs using LiteRT.js and the new Gemma 4 models. From revolutionizing special education to building autonomous web assistants, this event showcases the real impact of AI in the browser.Agenda & Speaker Details:1. Client-side Web AI Agents for the Agentic Internet of the FutureSpeaker: Jason Mayes (Web AI Lead, Google)Synopsis: The use of AI in JavaScript is growing exponentially. Jason will demonstrate how generative models from Google running entirely on the front end can exhibit agentic behaviour—giving your websites "superpowers" to automate tasks.Key Takeaways: Privacy, low latency, and zero inference costs.LANGUAGE: English | LEVEL: Intermediate | DURATION: 30 minutes2. WebAI Empowered Oculomotor Rehab for SEN ("Vision" Without Borders: WebAI-based Oculomotor Rehabilitation for Children with Special Educational Needs)Speakers:Cyrus Wong – Senior Lecturer, Hong Kong Institute of Information Technology (HKIIT) at IVE (Lee Wai Lee) & Google Developer Expert - Cloud(AI)Esther Cheung – Higher Diploma in Cloud and Data Centre Administration - Hong Kong Institute of Information Technology (HKIIT) at IVE (Lee Wai Lee) & GDG on Campus - HKIIT LeadSynopsis: Discover how WebAI breaks financial barriers in special education. Learn how a revolutionary cost-effective ecosystem leverages standard webcams to provide accurate eye tracking for children with Special Educational Needs (SEN).Technical Stack: MediaPipe Iris, WebGazer.js, LiteRT.js, and Gemma.Key Takeaways: High-precision eye tracking with no server costs; 100% data privacy for sensitive users.LANGUAGE: Cantonese | LEVEL: Intermediate | DURATION: 30 minutes3. Private and Offline: On-Device AI with LiteRT.js and Gemma 4Speaker: Connie Leung - GDE (Angular, AI, Web)Synopsis: Get hands-on experience with LiteRT.js and Google's open-source Gemma 4 models. Learn how to fetch models from Hugging Face and use WebGPU for high-performance in-browser inference.Key Takeaways: Setting up LiteRT-LM; optimizing WebGPU for browser acceleration; designing offline-first security.LANGUAGE: English | LEVEL: Intermediate | DURATION: 30 minutes4. Airplane Mode Agents: SKILL.md on a Phone and BrowserSpeaker: Sasha Denisov - CTO & Co-founder at Brainform.ai · Google Developer Expert (Flutter, Firebase, Cloud AI) & Maintainer of flutter_gemmaSynopsis: Running an AI model locally is nearly solved—determining what that model can and cannot do is the next big challenge. On-device agent skills require three main components: a portable description, discovery, and execution. While descriptions and discoveries have coalesced around markdown definitions and tool lists, execution remains fragmented across local code, native OS intents, and external tool calls (such as MCP servers). In this lightning session, Sasha introduces the unified skills layer built on top of flutter_gemma and demonstrates how simple SKILL.md files provide a single dispatch path for local, native, and external agent actions—even when fully offline in "Airplane Mode".Key Takeaways: Unified On-Device Execution - How to use portable SKILL.md files with flutter_gemma and LiteRT-LM to route local code, OS intents, and external tool calls via a single, offline-first dispatch path.LANGUAGE: English | LEVEL: Intermediate | DURATION: 10 minutes (Lightning Talk)Target audience / Requirements:Web developers (JavaScript/TypeScript/Flutter/Dart), AI enthusiasts, and tech professionals.Familiarity with web fundamentals (HTML/CSS/JS) is recommended.Please bring your own laptop to follow along with the live demos and code snippets.Event details:Date: August 19, 2026Time: 19:30 – 21:30 HKT (Check-in starts at 19:00)Location: Google Hong Kong, 21/F, Tower 2, Times Square, Causeway Bay.Light snacks and networking session included.=== Special thanks to our venue partner and snack sponsor Google Hong Kong ===