Git Stars Git Stars

#on-device-ai Repositories

Discover 68 active open source GitHub repositories tagged with #on-device-ai, accumulating 183,992 total stars (averaging 2,705 stars per project). Leading this topic is cactus-compute/cactus with 14,864 stars.

68
Total Repositories
183,992
Total Stars
2,705
Avg Stars/Repo
1
cactus-compute/cactus

Under-50 MB agentic, voice, and vision intelligence for consumer devices.

cactus-compute
โญ 14,864 Python ๐Ÿ‘ค cactus-compute Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-02-24
2
Edge0-AI/Edge0

Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads one step ahead. Mac, iPhone, Android, Windows.

Edge0-AI
โญ 12,176 C++ ๐Ÿ‘ค Edge0-AI Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-09-08
3
OpenBMB/MiniCPM

MiniCPM5: SOTA on-device LLMs, small yet powerful.

OpenBMB
โญ 11,898 Jupyter Notebook ๐Ÿ‘ค OpenBMB Organization ๐Ÿ• Updated 2026-11-09 ๐Ÿ“… Created 2024-01-29
4
RunanywhereAI/runanywhere-sdks

Production ready toolkit to run AI locally

RunanywhereAI
โญ 10,354 C++ ๐Ÿ‘ค RunanywhereAI Organization ๐Ÿ• Updated 2026-11-10 ๐Ÿ“… Created 2025-07-22
5
m87-labs/moondream

tiny vision language model

m87-labs
โญ 10,167 Python ๐Ÿ‘ค m87-labs Organization ๐Ÿ• Updated 2026-04-20 ๐Ÿ“… Created 2023-12-29
6
qualcomm/GenieX

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

qualcomm
โญ 8,544 Go ๐Ÿ‘ค qualcomm Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-08-16
7
apple-aiml-research/ml-fastvlm

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

apple-aiml-research
โญ 7,445 Python ๐Ÿ‘ค apple-aiml-research Organization ๐Ÿ• Updated 2026-09-11 ๐Ÿ“… Created 2025-05-01
8
drumih/turbo-fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

drumih
โญ 7,432 Swift ๐Ÿ‘ค drumih User ๐Ÿ• Updated 2026-11-14 ๐Ÿ“… Created 2026-07-17
9
google-ai-edge/LiteRT-LM

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

google-ai-edge
โญ 6,913 C++ ๐Ÿ‘ค google-ai-edge Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-04-14
10
neuphonic/neutts

On-device TTS model by Neuphonic

neuphonic
โญ 6,343 Python ๐Ÿ‘ค neuphonic Organization ๐Ÿ• Updated 2026-07-30 ๐Ÿ“… Created 2025-10-02
11
cactus-compute/engine

2-bit quantization, kernels, and runtime for consumer devices.

cactus-compute
โญ 6,200 C++ ๐Ÿ‘ค cactus-compute Organization ๐Ÿ• Updated 2026-11-05 ๐Ÿ“… Created 2025-04-23
12
Fractal-Compute-Orchestrations/FractalAndroid

A human-centric, resource-aware Android node for edge computing and federated learning. Orchestrates distributed intelligence with privacy-first localization and empathetic hardware management.

Fractal-Compute-Orchestrations
โญ 4,851 Kotlin ๐Ÿ‘ค Fractal-Compute-Orchestrations Organization ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2025-11-21
13
thunderbird/thunderbolt

AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.

thunderbird
โญ 4,827 TypeScript ๐Ÿ‘ค thunderbird Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-07-23
14
huggingface/smollm

Everything about the SmolLM and SmolVLM family of models

huggingface
โญ 3,960 Python ๐Ÿ‘ค huggingface Organization ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2024-11-04
15
XiaoMi
โญ 3,574 Python ๐Ÿ‘ค XiaoMi Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-11-06
16
nicedreamzapp/claude-code-local

Hit your Claude Code usage limit? Keep going free and offline on a local model: Qwen 3.8, Gemma 4, and Qwen 4 the day it ships. Runs on Apple Silicon Macs (MLX), Linux and Windows (llama.cpp) with no API key. Your code stays home.

nicedreamzapp
โญ 3,525 Python ๐Ÿ‘ค nicedreamzapp User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-26
17
QiuYannnn/Local-File-Organizer

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

QiuYannnn
โญ 3,069 Python ๐Ÿ‘ค QiuYannnn User ๐Ÿ• Updated 2024-10-21 ๐Ÿ“… Created 2024-09-21
18
Mininglamp-AI/Mano-P

Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook โ€” no data leaves your device. Mano-P is an open-source GUI-VLA project that supports local inference on Mac mini/MacBook or via compute stick, enabling purely vision-driven cross-platform GUI automation operations. Data is processed entirely locally, supporting planning and execution of complex multi-step tasks.

Mininglamp-AI
โญ 2,855 ๐Ÿ‘ค Mininglamp-AI Organization ๐Ÿ• Updated 2026-06-25 ๐Ÿ“… Created 2026-03-25
19
huggingface/swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion

huggingface
โญ 2,758 Swift ๐Ÿ‘ค huggingface Organization ๐Ÿ• Updated 2025-11-06 ๐Ÿ“… Created 2022-12-13
20
fikrikarim/parlor

On-device, real-time multimodal AI with features similar to GPT-Live

fikrikarim
โญ 2,117 Python ๐Ÿ‘ค fikrikarim User ๐Ÿ• Updated 2026-08-03 ๐Ÿ“… Created 2026-04-05
21
cosmo-wander-ai/cosmo-edge

Production-grade C++ edge AI engine for video analytics and on-device VLM across Sophon, Rockchip RKNN, and x86, with visual orchestration, real-time OSD, events, and reproducible benchmarks.

cosmo-wander-ai
โญ 2,106 C ๐Ÿ‘ค cosmo-wander-ai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-06-09
22
john-rocky/CoreML-Models

Core ML model zoo for iOS/macOS โ€” PyTorch models converted to ready-to-use .mlpackage, each with a conversion script and SwiftUI sample app. Sibling repos cover Apple's Core AI framework (iOS/macOS 27) and on-device LLMs.

john-rocky
โญ 1,902 Swift ๐Ÿ‘ค john-rocky User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2020-08-12
23
software-mansion/react-native-executorch

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

software-mansion
โญ 1,794 TypeScript ๐Ÿ‘ค software-mansion Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-10-16
24
nobodywho-ooo/nobodywho

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

nobodywho-ooo
โญ 1,699 Rust ๐Ÿ‘ค nobodywho-ooo Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2024-09-03
25
Muesli-HQ/muesli

Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow + Littlebird alternative)

Muesli-HQ
โญ 1,652 Swift ๐Ÿ‘ค Muesli-HQ Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-05
26
amicalhq/amical

Free, open-source voice typing for macOS and Windows. Local speech-to-text with Whisper and Parakeet, also works offline.

amicalhq
โญ 1,648 TypeScript ๐Ÿ‘ค amicalhq Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-05-08
27
mizorewww/laya-coreml

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

mizorewww
โญ 1,646 Python ๐Ÿ‘ค mizorewww User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-09-19
28
Neywa-Labs/nativ

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

Neywa-Labs
โญ 1,608 Swift ๐Ÿ‘ค Neywa-Labs Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-07-20
29
jxlpzqc/TMSpeech

Tencent Meeting "Moyu" Tool

jxlpzqc
โญ 1,504 C# ๐Ÿ‘ค jxlpzqc User ๐Ÿ• Updated 2026-07-15 ๐Ÿ“… Created 2023-06-20
30
ARahim3/mlx-tune

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning โ€” natively on MLX. Unsloth-compatible API.

ARahim3
โญ 1,475 Python ๐Ÿ‘ค ARahim3 User ๐Ÿ• Updated 2026-06-23 ๐Ÿ“… Created 2026-01-03
31
facebookresearch/MobileLLM

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

facebookresearch
โญ 1,471 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-04-30 ๐Ÿ“… Created 2024-07-09
32
mit-han-lab/proxylessnas

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

mit-han-lab
โญ 1,451 C++ ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-08-30 ๐Ÿ“… Created 2018-12-01
33
callstackincubator/ai

On-device LLM execution in React Native with Vercel AI SDK compatibility

callstackincubator
โญ 1,442 TypeScript ๐Ÿ‘ค callstackincubator Organization ๐Ÿ• Updated 2026-11-11 ๐Ÿ“… Created 2024-07-19
34
kellyvv/PhoneClaw

PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.

kellyvv
โญ 1,294 Swift ๐Ÿ‘ค kellyvv User ๐Ÿ• Updated 2026-08-06 ๐Ÿ“… Created 2026-04-04
35
rudrankriyam/Foundation-Models-Framework-Lab

A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

rudrankriyam
โญ 1,194 Swift ๐Ÿ‘ค rudrankriyam User ๐Ÿ• Updated 2026-11-07 ๐Ÿ“… Created 2025-06-09
36
agents-io/PokeClaw

PokeClaw (PocketClaw) โ€” first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

agents-io
โญ 1,165 Kotlin ๐Ÿ‘ค agents-io Organization ๐Ÿ• Updated 2026-06-02 ๐Ÿ“… Created 2026-04-06
37
chongzhou96/EdgeSAM

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

chongzhou96
โญ 1,152 Jupyter Notebook ๐Ÿ‘ค chongzhou96 User ๐Ÿ• Updated 2025-05-24 ๐Ÿ“… Created 2023-12-06
38
NativeMindBrowser/NativeMindExtension

NativeMind: Your fully private, open-source, on-device AI assistant

NativeMindBrowser
โญ 1,137 TypeScript ๐Ÿ‘ค NativeMindBrowser Organization ๐Ÿ• Updated 2026-03-23 ๐Ÿ“… Created 2025-06-05
39
google-ai-edge/litert-torch

Support PyTorch model conversion with LiteRT.

google-ai-edge
โญ 1,112 Jupyter Notebook ๐Ÿ‘ค google-ai-edge Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-05-13
40
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
41
intel/AI-Playground

AI PC starter app for doing AI image creation, image stylizing, and chatbot on a PC powered by an Intelยฎ Arcโ„ข GPU.

intel
โญ 1,043 TypeScript ๐Ÿ‘ค intel Organization ๐Ÿ• Updated 2026-10-30 ๐Ÿ“… Created 2024-07-10
42
kennss/SiliconScope

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

kennss
โญ 1,026 Swift ๐Ÿ‘ค kennss User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-06-08
43
facebookresearch/EdgeTAM

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

facebookresearch
โญ 1,024 Jupyter Notebook ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-01-27 ๐Ÿ“… Created 2024-12-13
44
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
45
mit-han-lab/TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

mit-han-lab
โญ 934 C++ ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-07-04 ๐Ÿ“… Created 2023-05-24
46
eclaire-labs/eclaire

Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-hosted, and extensible via APIs.

eclaire-labs
โญ 925 TypeScript ๐Ÿ‘ค eclaire-labs Organization ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2025-09-02
47
TheStageAI/TheWhisper

Optimized Whisper models for streaming and on-device use

TheStageAI
โญ 905 Python ๐Ÿ‘ค TheStageAI Organization ๐Ÿ• Updated 2026-10-31 ๐Ÿ“… Created 2025-10-19
48
gety-ai/apple-on-device-openai

OpenAI-compatible API server for Apple on-device models

gety-ai
โญ 891 Swift ๐Ÿ‘ค gety-ai Organization ๐Ÿ• Updated 2025-10-02 ๐Ÿ“… Created 2025-06-15
49
christopherkarani/Wax

Shared single-file memory layer for all your agents, sub-millisecond RAG over text, photos, and video on Apple Silicon. No server. No API. One file. Pure Swift.

christopherkarani
โญ 816 Swift ๐Ÿ‘ค christopherkarani User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-01-20
50
tetherto/qvac

Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.

tetherto
โญ 806 TypeScript ๐Ÿ‘ค tetherto Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-01-03

Frequently Asked Questions

1

What is the most popular #on-device-ai repository on GitHub?

The top ranked open source #on-device-ai project on GitHub is cactus-compute/cactus with 14,864 stars. Under-50 MB agentic, voice, and vision intelligence for consumer devices.

2

Which programming languages are most used in #on-device-ai repositories?

Among the top ranked #on-device-ai projects on GitHub, the most common programming languages are Python, Swift, C++, TypeScript.

3

How is the #on-device-ai repository ranking calculated?

We track 68 active open source repositories tagged with #on-device-ai (500+ stars), totaling 183,992 stars with an average of 2,705 stars per repository. Rankings update daily from the GitHub API.