Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
-
Updated
Sep 23, 2026 - Python
#
on-device-ai
Here are 1,846 public repositories matching this topic...
Production ready toolkit to run AI locally
android kotlin swift ios react-native web cpp inference edge flutter websdk vlm multimodal diffusion-models on-device-ai voice-ai llm llamacpp ollama apple-intelligence
-
Updated
Sep 24, 2026 - C++
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
macos swift metal gpgpu gemma on-device-ai apple-silicon llm llm-inference local-ai on-device-llm gemma4 gemma4-26b-a4b
-
Updated
Sep 22, 2026 - Swift
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
-
Updated
Sep 24, 2026 - C++
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
android ios arm mobile framework ai speech edge transformer smartphone whisper rag edge-ai on-device-ai mobile-inference quantiz llm llms llamacpp llm-inference
-
Updated
Sep 24, 2026 - C++
AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.
-
Updated
Sep 24, 2026 - TypeScript
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.
-
Updated
Oct 21, 2024 - Python
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.
macos llama airgap gemma mlx on-device-ai ai-privacy voice-ai apple-silicon ambient-computing browser-agent anthropic local-llm local-ai qwen offline-ai private-ai mlx-lm claude-code abliterated
-
Updated
Sep 20, 2026 - Python
Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacBook 上或通过算力棒本地运行推理，实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理，支持复杂多步骤任务规划与执行。
desktop-automation mano gui-automation edge-computing on-device-ai local-inference vision-language-action multimodal-ai gui-grounding osworld computer-use-agents visual-language-model mano-p
-
Updated
Jun 25, 2026
On-device, real-time multimodal AI with features similar to GPT-Live
python text-to-speech real-time speech-recognition gemma mlx voice-assistant multimodal kokoro on-device-ai apple-silicon local-llm litert-lm
-
Updated
Aug 3, 2026 - Python
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.
swift ios machine-learning deep-learning gan object-detection super-resolution semantic-segmentation coreml coremltools core-ai on-device-ai apple-silicon mlpackage
-
Updated
Sep 14, 2026 - Swift
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
text-to-speech ocr ai computer-vision object-detection speech-to-text vlm on-device-ai mobile-inference llm-inference react-native-ai executorch
-
Updated
Sep 24, 2026 - TypeScript
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
-
Updated
Aug 30, 2024 - C++
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
macos machine-learning text-to-speech deep-learning transformers speech-recognition speech-to-text lora whisper mlx peft huggingface on-device-ai apple-silicon large-language-models llm vision-language-model local-llm llm-finetuning unsloth
-
Updated
Jun 23, 2026 - Python
On-device LLM execution in React Native with Vercel AI SDK compatibility
-
Updated
Jul 7, 2026 - TypeScript
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.
decision-model coreml laya on-device-ai apple-silicon apple-neural-engine local-ai modernbert typed-decisions
-
Updated
Sep 22, 2026 - Python
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
kotlin python swift react-native ai tts godot godot-engine flutter slm stt expo inference-engine godot-plugin on-device-ai godot4 llm local-llm gguf python-llm
-
Updated
Sep 24, 2026 - Rust
Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)
macos speech-to-text transcription dictation agents meeting-notes privacy-first on-device-ai apple-silicon meeting-assistant
-
Updated
Sep 24, 2026 - Swift
PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.
swift ios gemma litert on-device-ai mobile-ai agent-framework ai-agent local-ai ollama local-agent mobile-agent on-device-agent mobile-ai-agent-framework mobile-agent-framework phone-ai-agent phone-harness phone-loop phone-agent-harness phone-agent-loop
-
Updated
Aug 6, 2026 - Swift
Add this topic to your repo
To associate your repository with the on-device-ai topic, visit your repo's landing page and select "manage topics."