Havuz

Native macOS image generator for FLUX.2 Klein — fully on-device on Apple Silicon via MLX. No Python, no ComfyUI, no server.

Local, real-time system-audio captioner + translator for macOS — Whisper + a local LLM + a glass overlay. Fully offline.

Local LLM chat app for Apple Silicon Macs.

Capture and transcribe macOS microphone, system, and per-app audio from a single native Swift CLI.

A native macOS app for understanding and reviewing AI-generated code — diffs, inline comments, and Claude Code & Codex agents in one place.

World's first Face Authentication enabled MacOS App-locker, completely free and open-source. Unlock your Mac apps using Face , TouchID or pa

Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-model

Debloat your Mac from the terminal: disable 307 non-essential macOS launchd services (Siri, Apple Intelligence, telemetry, ads) plus Spotlig

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

On-device live transcription and translation CLI for macOS 26+ on Apple Silicon

SiliconScope, Apple Silicon Mac’lerde sistem kaynaklarını ve özel hızlandırıcıları izleyen, ayrıca uzaktaki makineleri aynı panele ekleyebilen bir macOS monitörüdür.

Neden yükseliyor · 111 günde 966 yıldıza ulaşması ve son 28 günde 48 commit alması dikkat çekiyor; README’deki ANE ve memory-bandwidth ölçümleriyle uzaktaki makineleri tek panelde toplama özellikleri de ayırt edici bir kullanım vaadi sunuyor. Üç farklı yazar aktiviteye işaret etse de ekip genişliği sınırlı; yıldızlar tek başına benimseme veya kalite kanıtı değil.

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

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

The missing control knob for your Mac's SMC — fan curves, battery charge limits, power policy. Open-source, CLI-first.

Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

Fast, lean, open-source Docker Desktop alternative for Apple Silicon Macs.

Compare two local Persian (Farsi) speech-to-text models side by side: a Persian Whisper fine-tune vs. general large-v3, on Apple Silicon.

Native macOS menu bar app that keeps your MacBook awake for AI coding agents - Claude Code, OpenAI Codex, Cursor - even with the lid closed.

MLX-compatible REAP for pruning MoE models on Apple Silicon

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-

The free, open-source meeting-notes app for your Mac — offline transcription and AI notes, free in the cloud or 100% on-device.

Community-driven benchmark suite for MLX inference engines on Apple Silicon

Native macOS menu-bar fan control and charger-power monitor for Apple Silicon MacBook Pros.

Local-first native macOS terminal with Vietnamese IME support and coding-agent observability

macOS computer-use agent in the notch. Long-press, talk, Claude drives the mouse.

Local-first meeting recorder for Mac. Whisper on-device, your AI for summaries, MCP server for Claude Desktop.

Use your Intel iMac as an external display for Apple Silicon Macs — free, open source, via Thunderbolt Bridge

Run AI models on Apple Silicon and Raspberry Pi

Local AI model manager

Fast, private push-to-talk dictation for Apple Silicon Macs — local Parakeet TDT v3, no cloud or telemetry.

Run Claude Code with OpenRouter models while keeping tools, file editing, bash, MCP, VS Code support, smart caching, model switching, and sa

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Curso

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Local, private push-to-talk dictation for macOS. Hold a key, speak, release — your words appear in any text field. Runs entirely on-device v

The ready-to-use editor that nobody uses.

Big models. Small Macs. Zero excuses.

Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identif

macOS 語音聽寫 App — MLX Whisper + Breeze-ASR-25，完全離線，Apple Silicon 最佳化

Turn a Mac mini into a living-room retro/PS console - beautiful big-picture launcher (Electron + React)

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

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

Transformer inference via unconventional compute: a single algebraic primitive, a tag-system scheduler, and Apple's Neural Engine through co

Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with

Hands-free on-device voice loop for macOS: Apple SFSpeechRecognizer + cloned-voice TTS, continuous listening, zero cloud. Originally built t

A desktop app for creating and managing isolated Mac environments.

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

Turn your Mac into the brain of your household and operate from your phone.

Hermes Agent oturumlarını ve yönetim iş akışlarını macOS uygulamasından yerel olarak veya SSH üzerinden kullanmayı sağlar.

Neden yükseliyor · 2.021 yıldız, 172 günlük bir repo için kayda değer ilgiye işaret ediyor; README'de anlatılan Hermes iş akışlarını native Mac arayüzünde toplama yaklaşımı dikkat çekmiş olabilir. Ancak yıldızlar benimsenmeyi kanıtlamaz; son 28 günde commit ve farklı yazar yok, bu nedenle ilginin nedenini veya projenin güncel ivmesini doğrulamak mümkün değil.