#on-device-ai (26 Repositories)
Ranked open-source repositories tagged with #on-device-ai, scored by pull request acceptance likelihood and maintainer engagement velocity.
49.5%
44.9h
26 repositories tagged #on-device-ai
xybrid-ai/xybrid
Cross-platform on-device AI toolkit
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.
Sentient-OS-Labs/sentient-os
An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.
software-mansion/react-native-executorch
Declarative way to run AI models in React Native on device, powered by ExecuTorch.
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.
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.
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.
qualcomm/GenieX
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
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.
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.
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
RunanywhereAI/runanywhere-sdks
Production ready toolkit to run AI locally
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
cactus-compute/needle
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
Muesli-HQ/muesli
Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)
drumih/turbo-fieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
ShadowSafin/AndroLLM
Open-source Android AI using LiteRT-LM with hardware acceleration, cloud providers, memory, and voice.
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
zeraix/zeraix
Open-source local AI workspace — advancing on-device inference.
kellyvv/PhoneClaw
PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.
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.
Siddhesh2377/ToolNeuron
Encrypted & Privacy First, On Android Device AI App
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.
google-ai-edge/litert-samples
LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.
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).
bd4sur/Nano
电子鹦鹉 / Toy Language Model