Edge Computing and Artificial Intelligence of Things (AIoT) involve performing localized data processing directly on edge devices rather than relying entirely on centralized cloud servers. This architectural approach combines Internet of Things (IoT) hardware with optimized, lightweight machine learning models to enable real-time decision-making, drastically reduce network latency, and improve overall data privacy and bandwidth efficiency.
Open-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.
Deep learning gateway on Raspberry Pi and other edge devices
High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
Python Computer Vision & Video Analytics Framework With Batteries Included
an edge-real-time anchor-free object detector with decent performance
[CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications".
📸 PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with pretrained weights & state-of-the-art performance
A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.
A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning (DRL) for Mobile Edge Computing (MEC) | This algorithm captures the dynamics of the MEC environment by integrating the Dueling Double Deep Q-Network (D3QN) model with Long Short-Term Memory (LSTM) networks.
Neuralet is an open-source platform for edge deep learning models on edge TPU, Jetson Nano, and more.
Security camera with Raspberry pi and NVIDIA Jetson platforms
ProtoForge: 零硬件模拟 Modbus/S7/OPC-UA/BACnet 设备，测试上位机与网关通信。Python，开箱即用。
A unified ecosystem and workspace for large-scale federated learning, bridging the gap between centralized model evolution and decentralized edge intelligence.
ML model training for edge devices
NVIDIA Deepstream 6.1 Python boilerplate
Social Distancing Detector using deep learning and capable to run on edge AI devices such as NVIDIA Jetson, Google Coral, and more.
Containerized Development Environment Manager for embedded development