← GitHub Trending

GitHub topic

on-device-ai GitHub repositories

Explore 18 tracked GitHub repositories tagged on-device-ai. Compare their recorded star activity and implementation languages, then follow related topics to find other projects.

Snapshot: 2026-10-28. The collection gained 125 stars since the previous daily snapshot.

Tracked repositories: 18
Total stars: 53,865
Stars gained · 7 days: +641
Stars gained · 30 days: +2,754

Compare star activity

Up to five projects on this page, ordered by daily star growth. Open a project for its description and recorded star history.

Swipe to compare all star periods →

Star activity for on-device-ai repositories on this page
Repository	Total stars	Today	7 days	30 days
cactus-compute/needle	14.4K	+24	+212	+1,589
carloslfu/slotstream	595	+24	+24	+24
drumih/turbo-fieldfare	7.1K	+18	+107	+242
Sentient-OS-Labs/sentient-os	654	+16	+54	+130
Helldez/BigMoeOnEdge	678	+10	+37	+83

Explore repositories

Showing 1–18 of 18 tracked repositories.

cactus-compute/needle

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

★ 14.4K+24 todayPython

llm tool-calling

carloslfu/slotstream

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

★ 595+24 todaySwift

llm claude-code

drumih/turbo-fieldfare

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

★ 7.1K+18 todaySwift

Sentient-OS-Labs/sentient-os

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

★ 654+16 todaySwift

Helldez/BigMoeOnEdge

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

★ 678+10 todayC++

Muesli-HQ/muesli

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

★ 1.5K+7 todaySwift

nobodywho-ooo/nobodywho

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

★ 1.7K+5 todayRust

NightMean/OlliteRT

Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source

★ 583+4 todayKotlin

llm llm-inference

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.

callstackincubator/ai

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

★ 1.4K+3 todayTypeScript

qualcomm/GenieX

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

★ 8.5K+3 todayGo

DenisovAV/flutter_edge_ai

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

★ 649+2 todayDart

RunanywhereAI/runanywhere-sdks

Production ready toolkit to run AI locally

★ 10.3K+2 todayC++

john-rocky/CoreML-Models

Core ML model zoo for iOS/macOS — 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.

★ 1.9K+2 todaySwift

machine-learning deep-learning

kennss/SiliconScope

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

★ 1.0K+1 todaySwift

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.

★ 788+0 todaySwift

xybrid-ai/xybrid

Cross-platform on-device AI toolkit

★ 506+0 todayRust

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