apple-silicon

Run Stable Diffusion using Core ML on iOS within your Expo & React Native App

Private, local transcription and system-wide dictation for Apple Silicon.

Local LLM Testing & Benchmarking for Apple Silicon

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

Local, private voice dictation for macOS

M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.

Real-time on-device speech transcription + translation for macOS (Apple Silicon). Streaming ASR, speaker diarization, and live English→Chinese translation on Apple GPU/MLX — terminal CLI, no UI, no cloud.

A slightly opinionated Nix flake for ComfyUI with curated custom nodes. Supports macOS (Apple Silicon) and Linux with CUDA.

Synthetic Autonomic Mind - An AI assistant for everyone.

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI API compatible, zero API keys.

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.

Your computer was paying attention the whole time. 14-modality capture. Proactive intelligence. Computer-use training data. Native macOS. All on-device. Open source.

PersonaPlex on Apple Silicon: an MLX port of NVIDIA’s full-duplex speech-to-speech model with realtime local/web modes and offline WAV inference.

Open-source, offline voice-to-text for macOS. Hold a hotkey, speak, text appears. Private on-device dictation with multiple speech engines.

Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

Run local image, text, speech, vision, music, and video workflows, plus model management and a loopback OpenAI-compatible API server. The repo ships the core libraries and the mere.run executable.

Fix the 2-5 second push-to-talk activation delay on macOS. Keeps microphone hardware awake for instant voice transcription with AirPods, Bluetooth headsets, and built-in mic. Works with SuperWhisper, WhisperFlow, Wispr Flow, and any push-to-talk app on Apple Silicon (M1/M2/M3/M4).

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from scratch, locally on Apple Silicon with custom data, tokenizers, checkpoints, and MLX acceleration.

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Mac-native dictation that just works – lives in the notch, zero setup, free forever