Private on-device AI suite for Android. Fork of Google AI Edge Gallery with llama.cpp, whisper.cpp, stable-diffusion.cpp, GGUF import, voice chat, vision AI, on-device image generation, biometric lock, encrypted history, and CPU/NPU/GPU acceleration.

A demo app showcasing Vector Search using Azure AI Search, Azure OpenAI for text embeddings, and Azure AI Vision for image embeddings.

Read and Write Report (RAWR) Agent 🦖 an Nvidia AIQ Workflow template

16 channel, 4 models Vision AI demo, running on standalone DevKit

Generate voice narration for videos by analyzing frames with OpenAI's API and combine the narration with the video using `PHP-FFmpeg` to ensure seamless synchronization. Great for adding context or commentary to video content.

Detect text in image, using Autogon AI

A fun collection of notebooks for finetuning AI models... Share ready-to-run notebooks… tips & tricks for finetuning... Hugging Face Transformers, Unsloth, vLLM, PyTorch / CUDA magic

VisionVerse is a versatile tool that integrates image captioning, pre-trained image classification, and text-to-image generation.

Learning project: built a digit recognizer end-to-end — trained a CNN on MNIST, served it with Flask, and connected it to an HTML5 Canvas UI. 99.27% test accuracy.

Local, private lab report digitizer and dashboard — vision AI (Ollama), no data leaves your machine

Getting started with ROS2 on AMD's Kria KR260 Robotics Starter Kit

Multi-source RAG over SNAP public-assistance policy: semantic search with citations, cross-source gap detection, and AI-assisted policy authoring.

A modular, hybrid-intelligence AI assistant built with Python, utilizing Gemini and Ollama for system automation.