Back to Topics Directory
Topic Hub

#on-device-ai (26 Repositories)

Ranked open-source repositories tagged with #on-device-ai, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

49.5%

Avg Review Latency

44.9h

Filter by language

26 repositories tagged #on-device-ai

S TierRust 434 9 GFIs

xybrid-ai/xybrid

Cross-platform on-device AI toolkit

94.8%
Merge Rate
2d
First Review
50%
1st-Timers
8
Maintainers
B TierSwift 59

saurabhav88/EnviousWispr

Free, sub-second on-device AI dictation for macOS. Dual engines (Whisper + Parakeet) on Apple Silicon. Optional AI polish with our own on-device model (EG-1), Apple Intelligence (macOS 26), Ollama, or your own OpenAI/Gemini key. No account, no subscription, audio never leaves your Mac.

96.1%
Merge Rate
2d
First Review
100%
1st-Timers
1
Maintainers
A TierSwift 475

Sentient-OS-Labs/sentient-os

An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.

95.6%
Merge Rate
3d
First Review
50%
1st-Timers
19
Maintainers
A TierC++ 1.7k

software-mansion/react-native-executorch

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

88.5%
Merge Rate
4d
First Review
83%
1st-Timers
11
Maintainers
A TierSwift 131

pasrom/meeting-transcriber

On-device meeting transcriber for macOS — auto-records Teams/Zoom/Webex, transcribes & separates speakers locally. No cloud. Open-source alternative to Otter/Granola/Fireflies.

93.4%
Merge Rate
12d
First Review
67%
1st-Timers
11
Maintainers
A TierKotlin 541

sarim2000/pennywiseai-tracker

PennyWise automatically reads transaction SMS messages and transforms them into organized financial data with on-device AI assistance. No manual entry, no cloud processing, complete privacy.

87.7%
Merge Rate
7d
First Review
73%
1st-Timers
10
Maintainers
A TierSwift 742

SharpAI/SwiftLM

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

86.0%
Merge Rate
6h
First Review
67%
1st-Timers
3
Maintainers
A TierRust 8.3k

qualcomm/GenieX

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

77.1%
Merge Rate
16h
First Review
82%
1st-Timers
23
Maintainers
A TierSwift 552

leonickson1/Swiftlet

Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.

100.0%
Merge Rate
19h
First Review
100%
1st-Timers
2
Maintainers
A TierTypeScript 452

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.

71.4%
Merge Rate
1d
First Review
66%
1st-Timers
41
Maintainers
A TierSwift 162 11 GFIs

bitwize-ai/Logue

Privacy-first AI meeting notes & writing assistant for Mac — on-device transcription, smart minutes, action items & 60+ writing modes, running entirely on Apple Silicon

66.7%
Merge Rate
11h
First Review
50%
1st-Timers
5
Maintainers
A TierC++ 10.3k

RunanywhereAI/runanywhere-sdks

Production ready toolkit to run AI locally

70.9%
Merge Rate
13h
First Review
55%
1st-Timers
10
Maintainers
B TierSwift 790

christopherkarani/Wax

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

62.5%
Merge Rate
3d
First Review
100%
1st-Timers
0
Maintainers
B TierPython 9.7k

cactus-compute/needle

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

52.8%
Merge Rate
7h
First Review
29%
1st-Timers
24
Maintainers
B TierSwift 988 4 GFIs

Muesli-HQ/muesli

Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)

65.6%
Merge Rate
8d
First Review
53%
1st-Timers
24
Maintainers
B TierSwift 6.2k

drumih/turbo-fieldfare

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

41.1%
Merge Rate
11h
First Review
25%
1st-Timers
31
Maintainers
B TierKotlin 129

ShadowSafin/AndroLLM

Open-source Android AI using LiteRT-LM with hardware acceleration, cloud providers, memory, and voice.

33.3%
Merge Rate
1d
First Review
0%
1st-Timers
1
Maintainers
D TierKotlin 212

jegly/OfflineLLM

Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierTypeScript 354

zeraix/zeraix

Open-source local AI workspace — advancing on-device inference.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierSwift 1.2k

kellyvv/PhoneClaw

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

0.0%
Merge Rate
5h
First Review
0%
1st-Timers
1
Maintainers
C TierC++ 6.2k

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.

3.8%
Merge Rate
2d
First Review
0%
1st-Timers
64
Maintainers
D TierKotlin 466

Siddhesh2377/ToolNeuron

Encrypted & Privacy First, On Android Device AI App

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierKotlin 167

ritesh-kanwar/Cashiro

Cashiro is a comprehensive financial tracking manager that Turn bank SMS and PDF Statements into a clean, searchable money timeline with on-device AI assistance. 100% private, no cloud processing.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 408

google-ai-edge/litert-samples

LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierSwift 369

mutonby/shortcast

Native macOS app: drop a long video → auto-cut viral shorts, captioned for TikTok/Reels/YouTube, reframed to vertical, and scheduled. 100% on-device (Gemma 4 12B + WhisperKit + MLX).

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierC 296

bd4sur/Nano

电子鹦鹉 / Toy Language Model

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
Best On-device-ai Open Source Repositories & C-Rank™ | GetMerged