Havuz

qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS

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

Open-source (Apache 2.0) macOS database client in Swift & AppKit for PostgreSQL, MySQL, SQL Server, SQLite, Redis/Valkey, MongoDB, DynamoDB,

Live on-device captions for macOS system audio. Core Audio process tap + NVIDIA Parakeet / Nemotron on the Apple Neural Engine. 16 languages

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

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig

Fast and simple local PDF compression for macOS, Windows, and Linux. Drag, drop, done.

A native macOS companion for Draw Things: always-visible image and Moodboard inputs, a canvas you can draw on from an iPad (Sidecar), a loca

Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

A local-first workspace for documents, tasks and meetings on macOS — nested spaces, typed properties, relations and saved views, with transc

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

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

原生 macOS 远程工作台：SSH · SFTP · 终端 · RDP · 端口转发 · 主机监控 | Native macOS remote workbench

Thai + English voice typing for Mac. Offline speech-to-text that types Thai-spoken tech words in English. Push-to-talk dictation on Apple Si

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

Kesha listens and talks back: local speech to text and text to speech for agents and scripts, fastest on Apple Silicon.

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

Final macOS ipatool HTTP 403/SAP transition build; official fix is in majd/ipatool v2.4.0+.

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary, no

Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kern

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

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

Run AI models on Apple Silicon and Raspberry Pi

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and

Pure MLX MiniMax-H3 text-to-video-and-audio inference for Apple Silicon.

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

The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against t

Binders for macOS: local-first dictation, meeting notes and memory, with an MCP server for your AI tools. Private by design, free, open sour

Run GPT-OSS-120B on a 16 GB Mac. Streams mixture-of-experts weights from SSD so only the 2 GiB trunk stays resident. Swift + Metal, no depen

Let idle local LLMs sleep and get your Mac's memory back. A native macOS menu bar app to turn Ollama on and off and auto-free idle model RAM

macOS menu bar utility that keeps your Mac awake while AI coding agents are working, and lets it sleep when they're waiting for you.

Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via M

macOS 100 Power-User Tweaks & Interactive Terminal TUI/CLI (2026 - Tahoe Ready)

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

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

Gratis svensk tal-till-text som körs lokalt på din Mac eller Linux-dator. Transkribera intervjuer och möten offline med KB-Whisper och Klang

The last agentic harness you'll ever need. Bring any model; Pennant does the rest on your Mac and iPhone, and asks before anything is sent,

DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-

Native Mac dictation in a 12 MB download. Free Local mode with Whisper + Parakeet, reproducible benchmarks, optional Cloud. MIT-licensed cli

方寸智匣 LocalBrain：本地大模型、文件与媒体工作台。Apple Silicon Mac 2.3.0，Windows/Linux 2.2.9；Drama 3 本人克隆、长稿配音与分段修改，按平台维护运行环境。

Free, open-source system monitor widgets for Windows 10/11 and macOS on Apple Silicon (M1–M5): CPU, GPU, RAM, temperature, network and disk

NUEM, uyumlu MacBook’larda kapağın hareketine göre eşzamanlanan, özelleştirilebilir bir katlanma animasyonu sunan macOS menu bar uygulamasıdır.

Neden yükseliyor · Repo yalnızca 12 günlük ve 54 yıldızı var; bu erken ilgi gösteriyor, ancak neden yükseldiğini veya kullanımını doğrulayacak bağımsız kanıt sunulmuyor. Son 28 günde 5 commit’in tek yazardan gelmesi de etkinliğin henüz dar bir ekip tabanına sahip olduğunu gösteriyor.

On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.

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

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

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

Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches

First LLM Studio: local-first LLM workbench for Apple Silicon + MLX. 本地优先 LLM 工作台，覆盖 Agent、对比、微调、评测与运行时遥测。