sauravpanda/BrowserAI: Run local LLMs inside your browser

BrowserAI: Run LLMs in the Browser – Simple, Fast, and Open Source!

• 🔒 Privacy First: All processing happens locally – your data never leaves the browser
• 💰 Cost Effective: No server costs or complex infrastructure needed
• 🌐 Offline Capable: Models work offline after initial download
• 🚀 Blazing Fast: WebGPU acceleration for near-native performance
• 🎯 Developer Friendly: Simple API, multiple engine support, ready-to-use models

• Web developers building AI-powered applications
• Companies needing privacy-conscious AI solutions
• Researchers experimenting with browser-based AI
• Hobbyists exploring AI without infrastructure overhead

• 🎯 Run AI models directly in the browser – no server required!
• ⚡ WebGPU acceleration for blazing fast inference
• 🔄 Seamless switching between MLC and Transformers engines
• 📦 Pre-configured popular models ready to use
• 🛠️ Easy-to-use API for text generation and more

bash
npm install @browserai/browserai

OR

bash
yarn add @browserai/browserai

import { BrowserAI } from '@browserai/browserai';

const browserAI = new BrowserAI();

browserAI.loadModel('llama-3.2-1b-instruct');

const response = await browserAI.generateText('Hello, how are you?');
console.log(response);

const ai = new BrowserAI();
await ai.loadModel('llama-3.2-1b-instruct', {
  quantization: 'q4f16_1' // Optimize for size/speed
});

const response = await ai.generateText('Write a short poem about coding', {
  temperature: 0.8,
  maxTokens: 100
});

const ai = new BrowserAI();
await ai.loadModel('gemma-2b-it');

const response = await ai.generateText([
  { role: 'system', content: 'You are a helpful assistant.' },
  { role: 'user', content: 'What is WebGPU?' }
]);

const ai = new BrowserAI();
await ai.loadModel('whisper-tiny-en');

// Using the built-in recorder
await ai.startRecording();
const audioBlob = await ai.stopRecording();
const transcription = await ai.transcribeAudio(audioBlob);

const ai = new BrowserAI();
await ai.loadModel('speecht5-tts');
const audioBuffer = await ai.textToSpeech('Hello, how are you today?');
// Play the audio using Web Audio API
const audioContext = new AudioContext();
const source = audioContext.createBufferSource();
audioContext.decodeAudioData(audioBuffer, (buffer) => {
  source.buffer = buffer;
  source.connect(audioContext.destination);
  source.start(0);
});

More models will be added soon. Request a model by creating an issue.

• Llama-3.2-1b-Instruct
• SmolLM2-135M-Instruct
• SmolLM2-360M-Instruct
• SmolLM2-1.7B-Instruct
• Qwen-0.5B-Instruct
• Gemma-2B-IT
• TinyLlama-1.1B-Chat-v0.4
• Phi-3.5-mini-instruct
• Qwen2.5-1.5B-Instruct

• Llama-3.2-1b-Instruct
• Whisper-tiny-en (Speech Recognition)
• SpeechT5-TTS (Text-to-Speech)

• 🎯 Simplified model initialization
• 📊 Basic monitoring and metrics
• 🔍 Simple RAG implementation
• 🛠️ Developer tools integration

• 📚 Enhanced RAG capabilities
  • Hybrid search
  • Auto-chunking
  • Source tracking
• 📊 Advanced observability
  • Performance dashboards
  • Memory profiling
  • Error tracking

• 🔐 Security features
• 📈 Advanced analytics
• 🤝 Multi-model orchestration

We welcome contributions! Feel free to:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License – see the LICENSE file for details.

• MLC AI for their incredible mode compilation library and support for webgpu runtime and xgrammar
• Hugging Face and Xenova for their Transformers.js library, licensed under Apache License 2.0. The original code has been modified to work in a browser environment and converted to TypeScript.
• All our contributors and supporters!

Made with ❤️ for the AI community

• Modern browser with WebGPU support (Chrome 113+, Edge 113+, or equivalent)
• For models with shader-f16 requirement, hardware must support 16-bit floating point operations

Keep your files stored safely and securely with the SanDisk 2TB Extreme Portable SSD. With over 69,505 ratings and an impressive 4.6 out of 5 stars, this product has been purchased over 8K+ times in the past month. At only $129.99, this Amazon’s Choice product is a must-have for secure file storage.

Help keep private content private with the included password protection featuring 256-bit AES hardware encryption. Order now for just $129.99 on Amazon!