Maxim Salnikov

Privacy-first in-browser Generative AI web apps: offline-ready, future-proof, standards-based

What if you could run powerful AI in a web app with total user privacy, completely offline? New browser APIs make it possible.

Privacy-first in-browser Generative AI web apps: offline-ready, future-proof, standards-based
#1about 3 minutes

A demo of client-side AI using the NPU

A computer vision application performs image classification directly in the browser without any backend calls by leveraging the device's Neural Processing Unit (NPU).

#2about 3 minutes

The case for privacy-first, on-device AI

On-device AI meets user demands for performance, privacy, and offline access while satisfying developer needs for a unified codebase and helpful abstractions.

#3about 3 minutes

Introducing the Web Neural Network (WebNN) standard

The emerging WebNN standard provides a model-agnostic, unified abstraction for near-native AI execution in the browser, designed around practical use cases.

#4about 4 minutes

Leveraging hardware like the CPU, GPU, and NPU

WebNN can access all available hardware, with the NPU offering a power-efficient alternative to the GPU for sustained AI workloads on mobile devices.

#5about 6 minutes

Getting started with the low-level WebNN API

To experiment with the emerging WebNN standard, developers must use canary browser versions and enable specific flags, but its low-level API can be complex.

#6about 7 minutes

Simplifying development with high-level AI frameworks

Frameworks like ONNX Runtime Web and Transformers.js provide higher-level, task-based abstractions over WebNN, making it easier for app developers to build AI features.

#7about 3 minutes

Best practices and the future of browser AI

Focus on user experience by providing fallbacks and progress indicators, and look ahead to upcoming built-in browser APIs like the Prompt API that abstract away model management.

#8about 2 minutes

Demo code and using web workers for performance

The demo applications are built as offline-ready Progressive Web Apps and use Web Workers to run intensive AI computations without freezing the main UI thread.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

Key benefits of running AI in the browser
01:55 MIN

Key benefits of running AI in the browser

From ML to LLM: On-device AI in the Browser

The technology behind in-browser AI execution
02:20 MIN

The technology behind in-browser AI execution

Generative AI power on the web: making web apps smarter with WebGPU and WebNN

Implementing on-device AI with the Chrome AI API
11:35 MIN

Implementing on-device AI with the Chrome AI API

WeAreDevelopers LIVE – AI vs the Web & AI in Browsers

Two primary approaches for browser-based AI
01:41 MIN

Two primary approaches for browser-based AI

Prompt API & WebNN: The AI Revolution Right in Your Browser

The future of on-device AI in web development
01:14 MIN

The future of on-device AI in web development

Generative AI power on the web: making web apps smarter with WebGPU and WebNN

Performing inference in the browser with ONNX Runtime Web
09:27 MIN

Performing inference in the browser with ONNX Runtime Web

Making neural networks portable with ONNX

Introduction to generative AI in the browser
01:29 MIN

Introduction to generative AI in the browser

Generate AI in the Browser with Chrome AI - Raymond Camden

The future of on-device AI hardware and APIs
02:08 MIN

The future of on-device AI hardware and APIs

From ML to LLM: On-device AI in the Browser

Featured Partners

Related Videos

See all videos
Generative AI power on the web: making web apps smarter with WebGPU and WebNN32:27

Generative AI power on the web: making web apps smarter with WebGPU and WebNN

Christian Liebel

Prompt API & WebNN: The AI Revolution Right in Your Browser30:36

Prompt API & WebNN: The AI Revolution Right in Your Browser

Christian Liebel

Exploring the Future of Web AI with Google33:51

Exploring the Future of Web AI with Google

Thomas Steiner

From ML to LLM: On-device AI in the Browser27:23

From ML to LLM: On-device AI in the Browser

Nico Martin

Performant Architecture for a Fast Gen AI User Experience25:47

Performant Architecture for a Fast Gen AI User Experience

Nathaniel Okenwa

Generate AI in the Browser with Chrome AI - Raymond Camden36:41

Generate AI in the Browser with Chrome AI - Raymond Camden

Raymond Camden

How AI Models Get Smarter35:16

How AI Models Get Smarter

Ankit Patel

WeAreDevelopers LIVE – AI vs the Web & AI in Browsers53:46

WeAreDevelopers LIVE – AI vs the Web & AI in Browsers

Chris Heilmann, Daniel Cranney & Raymond Camden

Related Articles

View all articles
CH
Chris Heilmann
WebMCP: Empowering Agents as First-Class Citizens of the Web
WebMCP is an exciting W3C proposal that just landed in Chrome Canary to try out . The idea is that you can use some HTML attributes on a form or register JavaScript tool methods to give agents direct access to content. This gives us as content prov...
WebMCP: Empowering Agents as First-Class Citizens of the Web
AB
Adrien Book
How AI Will Eat The World 🤖
Of generative-AI-for-everything and synthetic pleasuresRemember the web3 hype? Tech bros with easy access to cheap liquidity wanted to create a decentralised, peer-to-peer internet powered by blockchain technology. Spoiler alert, it did not work. And...
How AI Will Eat The World 🤖
DC
Daniel Cranney
Dev Digest 198: 30 years of JS, In-Browser AI, How Attackers Abuse GenAI
Inside last week’s Dev Digest 198 . 🎂 30 years of JavaScript ⏰ How long is a JavaScript second 💻 Clean code in Angular 🤦‍♂️ AI makes different mistakes than humans 👨‍💻 In-browser and offline AI 🟠 Undocumented Hacker News features 🐋 DeepSeek censored...
Dev Digest 198: 30 years of JS, In-Browser AI, How Attackers Abuse GenAI

From learning to earning

Jobs that call for the skills explored in this talk.