World Congress 2025 Aug 20, 2025 Session details

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

Maxim Salnikov

Ditch costly cloud APIs and build fully private, offline-ready generative AI web apps. Run models locally using the WebNN API to ensure zero latency and absolute data privacy.

Pause
Mute Enter Fullscreen
#1 about 4 min

In-browser computer vision and NPU usage demo

Running a client-side image recognition task locally without backend APIs demonstrates basic offline capabilities.

#2 about 3 min

The case for native AI in web browsers

Performance constraints and privacy considerations drive the need to standardize local machine learning capabilities.

#3 about 3 min

Introducing the Web Neural Network API standard

The WebNN standard emerges as a hardware-agnostic layer to deliver near-native model execution.

#4 about 2 min

Overview of the Edge AI ecosystem and tech stack

Architectural layers connect underlying hardware silicon progressively up to high-level JavaScript application frameworks.

#5 about 5 min

Hardware acceleration with processors and neural units

Targeting different computing hardware optimizes throughput requirements and power efficiency limits for local operations.

#6 about 3 min

Setting up experimental browser flags and hardware drivers

Testing upcoming local machine learning features requires specific environment overrides and updated system drivers.

#7 about 2 min

Working with low-level WebNN execution graph logic

Constructing raw node execution arrays exposes deep complexity for frontend developers relying on specification bindings.

#8 about 3 min

Leveraging ONNX Runtime Web for local model execution

Higher-level runtime utilities simplify model loading syntax while directly routing calculations to web backends.

#9 about 4 min

Simplifying local AI tasks using the Transformers.js framework

Triggering specific multimodal tasks locally enables granular caching logic and seamless javascript dataset integrations.

#10 about 2 min

Best practices for user experience and large model caching

Building graceful local interactions relies on transparent download notifications and clear application state indicators.

#11 about 2 min

Using built-in browser Prompt APIs for language models

Offloading execution securely skips manual payload bundling entirely by hooking into a vendor's embedded assistant feature.

#12 about 2 min

Running AI applications with PWAs and background web workers

Web architectures isolate intense calculation models strictly to background processes to preserve responsiveness.

Matching moments

2:54 min

Leveraging Chrome AI and nano models for web applications

Raymond Camden · Perf + AI

2:17 min

Accelerating local machine learning models via WebNN

Christian Liebel Christian Liebel · WWC Europe 2026

4:41 min

Exploring agentic browsers and artificial intelligence generation

Chris Heilmann +2 · LIVE

2:46 min

Enhancing native browser experiences with on-device generative AI

Chris Heilmann +2 · LIVE

2:19 min

Drawbacks of cloud dependencies and local inference benefits

Christian Liebel Christian Liebel · WWC 2025

53 sec

The shift toward client-side agentic web development

Jason Mayes · Coffee With Developers

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Small LLM in your Browser: Huge Opportunities for Web Applications

Daniel Ostrovsky

UI/UX Architect at Payoneer | AI Architect | Full Cycle Development Expert | Public Speaker | Open Source Contributor |

Daniel Ostrovsky
Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Michael Yuan, Vivian Hu

Michael Yuan
Vivian Hu
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir
Open session

World Congress 2026 North America

Compute for your AI model: GPUs, LPUs, TPUs and beyond..

Kushaagra Goyal

Tech Lead at Rubrik, ex-CTO at Gan.AI, ex-Databricks

Kushaagra Goyal
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan