The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application

A Workflow-based Multi-platform AI Inference and Deployment Framework | 一款基于工作流的多端AI推理部署框架

oneAPI Data Analytics Library (oneDAL)

The easiest way to use Machine Learning. Mix and match underlying ML libraries and data set sources. Generate new datasets or modify existing ones with ease.

Cross-platform c++ sdk & model hub for easy ai inference

Client library to interact with various APIs used within Philips in a simple and uniform way

GPU-aware inference mesh for large-scale AI serving

Unity TTS plugin: Piper neural synthesis + OpenJTalk Japanese + Unity AI Inference Engine. Windows/Mac/Linux/Android ready. High-quality voices for games & apps.

Local LLM Inference Library

Customed version of Google's tflite-micro

No more Hugging Face cost leaks.

A powerful, faster, scalable full-stack boilerplace for AI inference using Node.js, Python, Redis, and Docker

Arbitrary Numbers

🌱 Intelligent IoT greenhouse fan controller using AI/ML for automated climate control. Features ESP32 + DHT22 sensors, real-time Firebase integration, Flutter mobile app with TensorFlow Lite on-device inference, and Wokwi simulation. Complete full-stack solution demonstrating IoT + AI integration.

UniUi uses AI to allow you to talk directly to your system.

AI Inference in GitHub Actions demo

Citadel AI OS – Enterprise AI Runtime Environment for Inference, Agents, and Business Operations