Git Stars Git Stars

#edge-ai Repositories

84
Total Repositories
340,999
Total Stars
4,059
Avg Stars/Repo
51
Helldez/BigMoeOnEdge

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, or edge device. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.

Helldez
โญ 1,066 C++ ๐Ÿ‘ค Helldez User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-07-10
52
LibreYOLO/libreyolo

LibreYOLO is a MIT licensed open source computer vision library

LibreYOLO
โญ 1,052 Python ๐Ÿ‘ค LibreYOLO Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2025-11-27
53
wangeai/K3Flight

Run Kimi K3 locally on CPU with ~55GB measured runtime RAM. A single-file Linux inference server powered by cPilot Runtime.

wangeai
โญ 1,019 HTML ๐Ÿ‘ค wangeai Organization ๐Ÿ• Updated 2026-07-31 ๐Ÿ“… Created 2026-07-30
โญ 983 TypeScript ๐Ÿ‘ค hinterdupfinger User ๐Ÿ• Updated 2024-06-21 ๐Ÿ“… Created 2023-09-19
55
luxonis/oak-examples

Example projects we've done with OAK cameras

luxonis
โญ 982 Python ๐Ÿ‘ค luxonis Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2020-05-27
56
feder-cr/jev

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices, and scores with probabilities, on your laptop's CPU.

feder-cr
โญ 970 C++ ๐Ÿ‘ค feder-cr User ๐Ÿ• Updated 2026-10-18 ๐Ÿ“… Created 2024-08-15
57
OpenSparX/MasterAgent

Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.

OpenSparX
โญ 966 C++ ๐Ÿ‘ค OpenSparX Organization ๐Ÿ• Updated 2026-09-28 ๐Ÿ“… Created 2026-08-10
58
microsoft/T-MAC

Low-bit LLM inference on CPU/NPU with lookup table

microsoft
โญ 964 C++ ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2025-06-05 ๐Ÿ“… Created 2024-02-02
59
facebookresearch/mobile-vision

Mobile vision models and code

facebookresearch
โญ 923 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2019-01-09
60
dog-qiuqiu/Yolo-FastestV2

:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+.

dog-qiuqiu
โญ 920 Python ๐Ÿ‘ค dog-qiuqiu User ๐Ÿ• Updated 2024-01-17 ๐Ÿ“… Created 2021-07-16
61
amd/RyzenAI-SW

AMD Ryzenโ„ข AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzenโ„ข AI powered PCs.

amd
โญ 902 Python ๐Ÿ‘ค amd Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2023-05-12
62
sourcenetwork/defradb

DefraDB is a Peer-to-Peer Edge-First Database. It's the core data storage system for the Source Ecosystem.

sourcenetwork
โญ 898 Go ๐Ÿ‘ค sourcenetwork Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2019-06-19
63
sipeed/MaixPy

Easily create AI projects with Python on edge device

sipeed
โญ 877 Python ๐Ÿ‘ค sipeed Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-01-20
64
ModelTC/MQBench

Model Quantization Benchmark

ModelTC
โญ 869 Python ๐Ÿ‘ค ModelTC Organization ๐Ÿ• Updated 2025-04-20 ๐Ÿ“… Created 2021-08-19
65
Pangu-Immortal/MagicWX

Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.

Pangu-Immortal
โญ 864 Kotlin ๐Ÿ‘ค Pangu-Immortal User ๐Ÿ• Updated 2026-11-09 ๐Ÿ“… Created 2019-05-08
66
Ampixa/sanoTTS

sanoTTS (เคธเคพเคจเฅ‹ = โ€œsmallโ€ in Nepali): a 294kโ€“2.27M-parameter neural TTS system that runs on a $3 chip, in the browser, or in Python, with low-latency streaming.

Ampixa
โญ 851 C ๐Ÿ‘ค Ampixa Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-07-11
67
nkasmanoff/pi-card

Raspberry Pi Voice Assistant

nkasmanoff
โญ 808 Python ๐Ÿ‘ค nkasmanoff User ๐Ÿ• Updated 2024-12-22 ๐Ÿ“… Created 2024-05-04
68
PaddlePaddle/Paddle-Lite-Demo

lib, demo, model, data

PaddlePaddle
โญ 799 C++ ๐Ÿ‘ค PaddlePaddle Organization ๐Ÿ• Updated 2025-09-17 ๐Ÿ“… Created 2019-08-21
69
fluxions-ai/vui

Vui Nano โ€” a small, context-aware text-to-speech model trained on real conversations. 219M active parameters (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Includes a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.

fluxions-ai
โญ 782 Python ๐Ÿ‘ค fluxions-ai Organization ๐Ÿ• Updated 2026-10-10 ๐Ÿ“… Created 2025-06-05
70
wenet-e2e/wekws

Production Ready End-to-End Keyword Spotting Toolkit

wenet-e2e
โญ 776 Python ๐Ÿ‘ค wenet-e2e Organization ๐Ÿ• Updated 2026-07-23 ๐Ÿ“… Created 2021-11-06
71
hailo-ai/hailo_model_zoo

The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment

hailo-ai
โญ 725 Python ๐Ÿ‘ค hailo-ai Organization ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2021-07-13
72
pnnx/pnnx

PyTorch Neural Network eXchange

pnnx
โญ 715 Python ๐Ÿ‘ค pnnx Organization ๐Ÿ• Updated 2026-11-10 ๐Ÿ“… Created 2021-02-09
73
SimonZeng7108/efficientsam3

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

SimonZeng7108
โญ 713 Jupyter Notebook ๐Ÿ‘ค SimonZeng7108 User ๐Ÿ• Updated 2026-08-11 ๐Ÿ“… Created 2025-10-16
74
Picovoice/speech-to-text-benchmark

speech to text benchmark framework

Picovoice
โญ 700 Python ๐Ÿ‘ค Picovoice Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2018-08-04
75
leafqycc/rknn-cpp-Multithreading

A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames). / A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames).

leafqycc
โญ 687 C ๐Ÿ‘ค leafqycc User ๐Ÿ• Updated 2024-04-09 ๐Ÿ“… Created 2023-05-05
76
DenisovAV/flutter_edge_ai

On-device AI for Flutter โ€” Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

DenisovAV
โญ 669 Dart ๐Ÿ‘ค DenisovAV User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-04-02
77
BasedHardware/Whomane

An open source wearable with camera

BasedHardware
โญ 613 TypeScript ๐Ÿ‘ค BasedHardware Organization ๐Ÿ• Updated 2024-05-12 ๐Ÿ“… Created 2024-03-05
78
Azure/AI-in-a-Box

AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions to the technical community. Our intent is to present a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction.

Azure
โญ 587 Jupyter Notebook ๐Ÿ‘ค Azure Organization ๐Ÿ• Updated 2024-12-12 ๐Ÿ“… Created 2023-08-31
79
kubeedge/sedna

AI took over KubeEdge

kubeedge
โญ 537 Go ๐Ÿ‘ค kubeedge Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2021-01-28
80
qijianpeng/awesome-edge-computing

A curated list of awesome edge computing, including frameworks, simulators, tools, etc.

qijianpeng
โญ 531 ๐Ÿ‘ค qijianpeng User ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2019-11-07
81
xybrid-ai/xybrid

Cross-platform on-device AI toolkit

xybrid-ai
โญ 527 Rust ๐Ÿ‘ค xybrid-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-12-13
82
NimbleEdge/deliteAI

On-device Agentic AI platform

NimbleEdge
โญ 519 C++ ๐Ÿ‘ค NimbleEdge Organization ๐Ÿ• Updated 2026-03-29 ๐Ÿ“… Created 2025-05-05
83
mantisfury/ArkhamMirror

Local-first AI-powered document intelligence platform for investigative journalism

mantisfury
โญ 507 Python ๐Ÿ‘ค mantisfury User ๐Ÿ• Updated 2026-01-25 ๐Ÿ“… Created 2025-11-25
84
mit-han-lab/tiny-training

On-Device Training Under 256KB Memory [NeurIPS'22]

mit-han-lab
โญ 505 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-03-29 ๐Ÿ“… Created 2022-11-15