AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.
TypeScript SDK for different in-browser AI model providers, built to make client-side AI integration simpler and more consistent across vendors.
Browser-native vector database built in Rust and compiled to WebAssembly for client-side embedding storage and semantic search.
PDF redaction that runs entirely on your device. Five detection layers including Gemma 4 contextual PHI. No uploads, no servers, no leaks.
Privacy-first, browser-based text-to-speech studio powered by Kokoro. Generate and download natural speech locally with no backend or data collection.
Real-time facial emotion recognition running entirely in the browser built with React, TensorFlow.js, and a custom-trained CNN model.
Crab-Agent is an LLM-powered Chrome extension that automates browser tasks using natural language commands. Inspired by Claude for Chrome
Una extensión de Chrome que permite corregir, traducir, resumir y crear textos mediante IA integrada en el navegador o en la nube.
Worker pool for running AI models in the browser — WebGPU/WASM auto-detection, streaming, cross-tab dedup
Run Google's Gemma 4 entirely in your browser via WebGPU. Multimodal chat, E2B vs E4B arena, ONNX conversion toolkit.
An intelligent, AI-powered job application automation system. This system can automatically navigate job sites, fill application forms, upload resumes, and submit applications with comprehensive reporting and analytics.
A 36M-parameter goldfish language model with a 10-second memory + pixel-art PWA desk pet. Runs in your browser, fully offline. Adopt it at den-sec.github.io/glublm/desk-pet/
An open-source NPM package abstracting complex multi-threaded orchestration in browsers—including web worker offloading, ping-pong synchronization, and zero-copy transfers—for zero-friction, idiomatic integration of Google MediaPipe API in React.js and Next.js with full SSR-safety.
Google for Pakistan
Bounded-latency browser edge inference pipeline for real-time voice interview summarization using ONNX Runtime Web + WASM. Features Web Worker isolation, semantic ring buffers, latest-only concurrency control, observability dashboard, offline-first architecture and production-ready whisper.cpp upgrade path.
Production-grade edge AI inference platform running fully in the browser with zero backend, local model execution, and mission-control UI.
Free, private AI in your browser
Add a description, image, and links to the browser-ai topic page so that developers can more easily learn about it.
To associate your repository with the browser-ai topic, visit your repo's landing page and select "manage topics."