About

Browser AI Chat runs entirely in your browser. There is no server, no API keys, and your data never leaves your device. It supports multiple local AI backends:

Gemini Nano via Chrome’s built-in AI APIs
Transformers.js for running Hugging Face models in-browser
WebLLM for larger models via WebGPU

Why I built it

I wanted to see how far client-side AI had come. As browser capabilities improve (WebGPU, built-in AI APIs), more AI workloads can run locally without losing too much quality. This project is a testbed for those possibilities.

What I owned

Designed the full client-only app architecture
Integrated multiple local AI runtimes behind one chat experience
Built local persistence for conversation history and attachments
Shipped the project as an installable PWA without backend infrastructure

Features

Local AI models: Built-in AI (Gemini Nano), Transformers.js, WebLLM
Model switching: Move between backends in one chat experience
WebGPU acceleration where available
Complete privacy: All processing happens in your browser
Multi-modal: Text, images, documents, audio
Offline: Works without internet after setup
PWA: Install like a native app
File support: Drag-and-drop attachments
Local history: Conversations stored in IndexedDB

Tech stack

React + TypeScript + TailwindCSS
Vite + PWA
TanStack Router
IndexedDB (Dexie)

What this shows

This project shows the kind of AI product engineering I enjoy: understanding new platform capabilities, designing a practical abstraction around messy runtime differences, and shipping a product that users can try directly.

Development

git clone https://github.com/bimsina/browser-chat.git
pnpm install
pnpm dev

Model types

Built-in AI: Browser native (Chrome and Edge only), instant startup

Chrome’s Built-in AI

Transformers.js: ONNX models, good variety, medium size

Transformers.js

WebLLM: Large models, most capable, bigger downloads

WebLLM

Browser support

Chrome and Edge: Full support
Firefox: Transformers.js + WebLLM
Safari: Transformers.js only