A ready-to-use, minimal app that converts any speech into text.
-
Updated
Jul 5, 2024 - JavaScript
A ready-to-use, minimal app that converts any speech into text.
Electron + Next.js desktop AI assistant that runs GGUF models locally using llama.cpp. Designed for offline use, portability, and zero-install deployment.
A collection of Agent Skills for building iOS/macOS applications with Apple's Foundation Models framework (Apple Intelligence). These skills are designed for zero-friction AI-assisted development with on-device models.
Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apache 2.0 · on-device AI · function calling
Local-first AI medical scribe running entirely in the browser using Chrome built-in AI (no backend)
A Google Photos alternative, where your pictures never leave your phone! Classification happens on-device, leveraging pre-trained models. Available for Android and iOS.
Object detection inference with Roboflow Train models on NVIDIA Jetson devices.
On-device wake-phrase detection in the browser — WebAssembly + SIMD128, ~275 KB total (runtime + model), no server. Same runtime as voxrt-wake-word-{android,ios,linux}. Free demo tier of the VoxRT wake-word family.
On-device 14-way keyword spotting in the browser — WebAssembly + SIMD128, ~1.5 MB total (runtime + model), no server. Same runtime as voxrt-kws-{linux,android,ios}.
AI-powered browsing assistant for Chrome. Built for the Google Chrome Built-in AI Challenge 2025.
R.E.D.A.C.T (Restricting Exposed Data by Anonymization for Confidential Transmission) is an Electron-based application that helps you redact personal information from text documents and clipboard content.
📸 High-speed P2P photo transfer & private local AI gallery (AirDrop alternative with on-device MobileCLIP search & face clustering)
Next.js chat demo that runs entirely on Chrome's built-in on-device model through the window.ai text-session API. Tailwind UI, no server-side inference.
🧍 Privacy-first desktop app that improves your posture via on-device webcam tracking
Local Chrome extension for browser-side AI-image signals. No image uploads. MIT.
A Chrome extension that summarises web pages, answers questions, and generates quizzes — entirely on-device with unlimited offline usage.
AI-powered Chrome extension that makes any web article accessible — on-device LLM via WebGPU, zero cloud, zero backend. Built for dyslexia, ADHD, low vision, and everyone in between.
Use browser-provided, on-device language models from Blazor through Microsoft.Extensions.AI and the Prompt API.
Run model GGUF gui esay ,faster,localy 100%
To associate your repository with the on-device-ai topic, visit your repo's landing page and select "manage topics."