Tags: #edge-ai

MNN is a blazing-fast, lightweight deep learning inference engine optimized for high-performance on-device AI and Large Language Models.

A local AI API platform for running various AI models (vision, speech, language) on diverse hardware with an OpenAI-compatible API.

Autodistill automates the process of training small, fast supervised models from unlabeled images by leveraging large foundation models, eliminating the need for manual data labeling.

A lightweight C++ inference library designed to run large ONNX-based AI models like Stable Diffusion XL and Mistral 7B on resource-constrained devices with minimal memory footprint.

MimiClaw transforms a $5 ESP32-S3 chip into a personal AI assistant, offering Telegram integration, local memory, and ultra-low power consumption without a traditional OS.

Supertonic is a lightning-fast, on-device, multilingual text-to-speech system offering high-quality audio and privacy without cloud dependencies.