{"id":13684929,"url":"https://github.com/rcmalli/awesome-edge-ai","last_synced_at":"2025-05-07T15:01:35.980Z","repository":{"id":37548370,"uuid":"173460732","full_name":"rcmalli/awesome-edge-ai","owner":"rcmalli","description":"A curated list of edge tools for AI applications","archived":false,"fork":false,"pushed_at":"2019-11-14T10:35:16.000Z","size":23,"stargazers_count":50,"open_issues_count":0,"forks_count":13,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-30T12:20:11.149Z","etag":null,"topics":["awesome-list","deep-learning","edge-ai","embedded-systems","iot"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rcmalli.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-03-02T14:55:33.000Z","updated_at":"2025-01-18T15:00:54.000Z","dependencies_parsed_at":"2022-08-02T02:20:05.958Z","dependency_job_id":null,"html_url":"https://github.com/rcmalli/awesome-edge-ai","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rcmalli%2Fawesome-edge-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rcmalli%2Fawesome-edge-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rcmalli%2Fawesome-edge-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rcmalli%2Fawesome-edge-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rcmalli","download_url":"https://codeload.github.com/rcmalli/awesome-edge-ai/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252761125,"owners_count":21800124,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["awesome-list","deep-learning","edge-ai","embedded-systems","iot"],"created_at":"2024-08-02T14:00:40.774Z","updated_at":"2025-05-07T15:01:35.947Z","avatar_url":"https://github.com/rcmalli.png","language":null,"funding_links":[],"categories":["Other awesome AI lists","Related awesome lists"],"sub_categories":["Misc"],"readme":"# awesome-edge-ai [![Awesome][awesome-badge]](https://github.com/sindresorhus/awesome) [![Build Status](https://travis-ci.org/rcmalli/awesome-edge-ai.svg?branch=master)](https://travis-ci.org/rcmalli/awesome-edge-ai)\n\nA curated list of edge devices for AI applications.\n\n## Contents\n\n- [Development Platforms](#development-platforms)\n- [Custom Accelerators](#custom-accelerators)\n- [Software Libraries](#software-libraries)\n\n\n### Development Platforms\n\u003c!-- Section description (optional). --\u003e\n\n- [Baidu EdgeBoard](http://ai.baidu.com/tech/hardware/deepkit) - Xilinx FPGA based edge computing board.\n- [BeagleBone AI](https://beagleboard.org/ai) - Linux Board powered by ARM CPU,TI C66x digital-signal-processor (DSP) cores and embedded-vision-engine (EVE). It has 1GB RAM.\n- [Google Coral Dev Board](https://coral.withgoogle.com/products/dev-board/) - It is single board solution which contains ARM CPU and Edge TPU as accelerator with 1GB RAM.\n- [Google Coral USB Accelerator](https://coral.withgoogle.com/products/accelerator/) - Edge TPU  accelerator module connects with USB interface. It needs host device.\n- [Intel Neural Compute Stick 1](https://software.intel.com/en-us/movidius-ncs) - First generation ASIC chip designed by Movidius that runs as module board via USB interface. It needs host device.\n- [Intel Neural Compute Stick 2](https://www.intel.ai/intel-neural-compute-stick-2-smarter-faster-plug-and-play-ai-at-the-edge/) - Second generation module stick which is faster than previous one based TOPS measure. It needs host device.\n- [Nvidia Jetson AGX Xavier](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-agx-xavier/) - Most power single board computer from NVIDIA designed for autonomous systems (cars etc.). Contains 512 Cuda core Volta GPU with Tensor Cores and 16 GB RAM.\n- [Nvidia Jetson Nano](https://devblogs.nvidia.com/jetson-nano-ai-computing/) - Cost efficient alternative to NVIDIA boards. Performance is equivalent to the TX1. Contains ARM CPU and 128 Cuda core Maxwell GPU and has 4 GB RAM.\n- [Nvidia Jetson TX1](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems-dev-kits-modules/?section=jetsonTX1) - Contains ARM CPU and 128 Cuda core Maxwell GPU. `It seems like this board is replaced by Nano.` \n- [Nvidia Jetson TX2](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems-dev-kits-modules/?section=jetsonTX2) - Contains ARM CPU and 256 Cuda core Pascal GPU and has 8 GB/4 GB RAM.\n- [OrangePi AI Stick](http://www.orangepi.org/Orange%20Pi%20AI%20Stick%202801/) - ASIC based neural accelerator. It needs host device.\n- [Sipeed MAIX Go Suit](https://www.indiegogo.com/projects/sipeed-maix-the-world-first-risc-v-64-ai-module) - Single board computer based on RISC-V AI chip, KPU(Neural Network Processor) and APU(Audio Processor). It contains on-board DVP camera and LCD screen for visual output.\n- [SmartEdge Agile](https://www.avnet.com/wps/portal/integrated/solutions/capabilities/smartedge-agile/) - Modular Edge Device with IOT capabilities.\n- [SparkFun Edge Development Board](https://www.sparkfun.com/products/15170) - Apollo3 Blue microcontroller based board that contains microphones and 3-axis accelerometer and OV7670 camera interface. Runs on single coin battery. Supports Tensorflow-lite.\n- [UP Squared AI Vision X](https://up-shop.org/home/285-up-squared-ai-vision-x-developer-kit.html) - Single board computer contains Intel ATOM CPU and Movidius Myriad as neural accelerator. It has 4 GB RAM.\n- [Xnor.ai Solar Powered Module](https://www.xnor.ai/solar-powered-ai/) - Very low power unit which can be running with only using solar panels. `More technical specifications needed.`\n\n\n### Custom Accelerators\n- [Google Edge TPU](https://cloud.google.com/edge-tpu/)\n- [Intel Movidius Myriad VPU 2](https://www.movidius.com/myriad2)\n- [Intel Movidius Myriad X VPU](https://www.movidius.com/myriadx)\n- [Kendryte K210](https://kendryte.com/)\n- [Lightspeeur 280-X Neural Accelerators](https://www.gyrfalcontech.ai/solutions/)\n- [Sipeed MAIX](https://www.indiegogo.com/projects/sipeed-maix-the-world-first-risc-v-64-ai-module#/)\n- TI Vision AcclerationPac\n\n### Software Libraries\n\n- [Tensorflow Lite](https://www.tensorflow.org/lite)\n- [TinyDNN](https://github.com/tiny-dnn/tiny-dnn)\n- [uTensor](https://github.com/uTensor/uTensor)\n- [EdgeML](https://github.com/Microsoft/EdgeML)\n- [nncase](https://github.com/kendryte/nncase)\n\n## Contribute\nContributions welcome! Read the [contribution guidelines](CONTRIBUTING.md) first.\n\n## License\n[![CC0](http://mirrors.creativecommons.org/presskit/buttons/88x31/svg/cc-zero.svg)](https://creativecommons.org/publicdomain/zero/1.0/)\n\nTo the extent possible under law, Refik Can MALLI has waived all copyright\nand related or neighboring rights to this work. See [LICENSE](LICENSE).\n\n\n\u003c!-- BADGES --\u003e\n\n[awesome-badge]: https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frcmalli%2Fawesome-edge-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frcmalli%2Fawesome-edge-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frcmalli%2Fawesome-edge-ai/lists"}