LocalWebAI

LocalWebAI is a browser-native framework for running AI models locally using WebGPU and WebAssembly.

It enables semantic search, retrieval-augmented generation (RAG), and on-device personalization directly in static web applications — without requiring any backend infrastructure.

🚀 Motivation

Researchers and developers often publish content via static hosting platforms (e.g., GitHub Pages) due to cost and simplicity. However, adding intelligent features such as:

• semantic search
• natural language querying
• contextual recommendations

typically requires server-side infrastructure or paid APIs.

LocalWebAI removes this dependency by enabling fully local inference in the browser.

✨ Features

• 🧠 Local LLM inference (WebGPU + WASM)
• 🔍 Retrieval-Augmented Generation (RAG)
• 📚 Semantic search over documents
• 🔒 Privacy-preserving (no data leaves the browser)
• ⚡ Zero server infrastructure
• 🎯 On-device personalization (planned)

📦 Installation

npm install localwebai