openedge - Extend cloud computing, data and service seamlessly to edge devices.

•    Go

OpenEdge is an open edge computing framework that extends cloud computing, data and service seamlessly to edge devices. It can provide temporary offline, low-latency computing services, and include device connect, message routing, remote synchronization, function computing, video access pre-processing, AI inference, etc. The combination of OpenEdge and the Cloud Management Suite of BIE(Baidu IntelliEdge) will achieve cloud management and application distribution, enable applications running on edge devices and meet all kinds of edge computing scenario. About architecture design, OpenEdge takes modularization and containerization design mode. Based on the modular design pattern, OpenEdge splits the product to multiple modules, and make sure each one of them is a separate, independent module. In general, OpenEdge can fully meet the conscientious needs of users to deploy on demand. Besides, OpenEdge also takes containerization design mode to build images. Due to the cross-platform characteristics of docker to ensure the running environment of each operating system is consistent. In addition, OpenEdge also isolates and limits the resources of containers, and allocates the CPU, memory and other resources of each running instance accurately to improve the efficiency of resource utilization.

Awesome-System-for-Machine-Learning - A curated list of research in machine learning system

A curated list of research in machine learning system. Link to the code if available is also present. Now we have a team to maintain this project. You are very welcome to pull request by using our template.

yomo - 🦖 Serverless Streaming Framework for Low-latency Edge Computing applications, running atop QUIC protocol, as Metaverse infrastructure, engaging 5G technology

•    Go

YoMo is an open-source Streaming Serverless Framework for building Low-latency Edge Computing applications. Built atop QUIC Transport Protocol and Functional Reactive Programming interface. makes real-time data processing reliable, secure, and easy. Congratulations! You have done your first YoMo Stream Function.

kubeedge - Kubernetes Native Edge Computing Management Framework

•    Go

KubeEdge is an open source system extending native containerized application orchestration and device management to hosts at Edge. It is built upon Kubernetes and provides core infrastructure support for network, app. deployment and metadata synchronization between cloud and edge. It also supports MQTT and allows developers to author customer logic and enable resource constraint devices communication at Edge. With business logic running at Edge, volumes of data can be secured & processed locally. It reduces the bandwidth request between Edge and Cloud; increases the response speak; and protects customers' data privacy.

ops - ops - build and run nanos unikernels

•    Go

Ops is a tool for creating and running a Nanos unikernel. It is used to package, create and run your application as a nanos unikernel instance. Building from source is easy if you have used Go before.

zenoh - zenoh unifies data in motion, data in-use, data at rest and computations

•    Rust

The Eclipse zenoh: Zero Overhead Pub/sub, Store/Query and Compute. Eclipse zenoh (pronounce /zeno/) unifies data in motion, data in-use, data at rest and computations. It carefully blends traditional pub/sub with geo-distributed storages, queries and computations, while retaining a level of time and space efficiency that is well beyond any of the mainstream stacks.

fastseg - 📸 PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with pretrained weights & state-of-the-art performance

•    Python

This respository aims to provide accurate real-time semantic segmentation code for mobile devices in PyTorch, with pretrained weights on Cityscapes. This can be used for efficient segmentation on a variety of real-world street images, including datasets like Mapillary Vistas, KITTI, and CamVid. The models are implementations of MobileNetV3 (both large and small variants) with a modified segmentation head based on LR-ASPP. The top model was able to achieve 72.3% mIoU accuracy on Cityscapes val, while running at up to 37.3 FPS on a GPU. Please see below for detailed benchmarks.

fog05 - End-to-End Compute, Storage and Networking Virtualisation.

•    Python

You need a running YAKS server to use it.

datacollector-edge - StreamSets Data Collector Edge (SDC Edge)

•    Go

The StreamSets Data Collector Edge (SDC Edge) enables at-scale data ingestion and analytics for edge systems. An ultralight, small-footprint agent, it is an ideal solution for use cases like Internet of Things (IoT) or cybersecurity applications that collect data from resource-constrained sensors and personal devices. StreamSets Data Collector Edge is built on open source technologies, our code is licensed with the Apache License 2.0.

ncs - Movidius Neural Compute Stick V2.0 API Go bindings

•    Go

The Movidius NCSDK API coverage provided in this repo should give you all the tools to use Movidius NCS to perform Neural Network inference.

galaxy - Galaxy decentralized node network and protocol

•    Go

There are currently two supported operating system installations for Galaxy Core Software. Installation.

fly - Open source Edge Application runtime

•    TypeScript

The Fly runtime is an open source Javascript environment built to run Edge Applications. It gives developers powerful caching, content modification, and routing tools. The runtime is based on v8, with a proxy-appropriate set of Javascript libraries. There are built in APIs for manipulating HTML and Image content, low level caching, and HTTP requests/responses. When possible, we use WhatWG standards (like fetch, Request, Response, Cache, ReadableStream).

stuart - A Lua-based Apache Spark runtime for embedding and edge computing

•    Lua

(He's little). A pure Lua rewrite of Apache Spark 2.2, designed for embedding and edge computing.

fogflow - FogFlow is a distributed execution framework to support dynamic processing flows over cloud and edges

•    Go

FogFlow is an IoT edge computing framework to automatically orchestrate dynamic data processing flows over cloud and edges driven by context, including system context on the available system resources from all layers, data context on the registered metadata of all available data entities, and also usage context on the expected QoS defined by users. This project is part of FIWARE. For more information check the FIWARE Catalogue entry for Processing.

rules - Golang based Rules for Real-time Contextual Decisions

•    Go

Rules is a lightweight library written in Golang to simplify the building of contextually aware, declaritive rules. Getting started should be fairly easy. Lets start off with some definitions around various types used.

duedge-recipes - DuEdge百度边缘网络计算样例代码

•    Javascript

duedge 为租户提供 FaaS(Serverless) 服务, 租户可以将功能函数运行在 Edge 端 (cdn 节点), 实现边缘计算应用场景.

neardb - Simple document db made for infinitely scalable globally distributed reads.

•    TypeScript

NearDB is a simple database that leverages cloud infrastructure like document storage and CDN to deliver an inexpensive unbelievably scalable document database optimized for reads and perfect for edge applications. While working on building edge applications for higher performance and lower latency there is a need store persistent data also on edge.

gcloud-iot-edge-tensorflow - Asset Tracking using Edge Computing and Computer Vision.

•    C

A bunch of ESP32 with camera, a local server (probablye a raspberry pi ) running image classification and object detection using Tensorflow and sending the data to processed data to Google Cloud. Depending on your model, change on the platformio.ini file the env_default configuration depending on your board (m5cam or esp32cam). Also you need to change the Wifi credentials on the sdkconfig.h file ( CONFIG_WIFI_SSID and CONFIG_WIFI_PASSWORD).

cloudflare-typescript-workers - Types and mocks for building a tested Typescript Cloudflare Worker, generates three NPM packages

•    TypeScript

Cloudflare Workers allow you to run JavaScript on Cloudflare's edge servers around the world. You can modify your site’s HTTP requests and responses, make parallel requests, or generate responses from the edge. This project develops, tests, and deploys NPM packages supporting the development of Cloudflare Workers using TypeScript. Get started on your own TypeScript Cloudflare Worker using the Template.

ncs - Movidius Neural Compute Stick V2.0 API Go bindings

•    Go

The Movidius NCSDK API coverage provided in this repo should give you all the tools to use Movidius NCS to perform Neural Network inference.