Havuz

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

chad: a coding agent for your macbook pro

Native macOS menu bar app & CLI to see what is listening on localhost, identify projects & processes, and gently close them. The safer alter

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

A native Git workspace for macOS, with local and SSH repositories, worktrees, and AI commit messages.

Native Codex account switcher by Zhao Liu (liuzhao1225) for macOS and Windows. Local accounts, weekly/5h usage, confirmed Desktop switching.

Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide

The ready-to-use editor that nobody uses.

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

Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built

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

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

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

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

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

Native open-source system monitor for macOS — Apple Silicon, SMC sensors, processes, disks, network and system health.

Terminal system monitor for Apple Silicon Macs: CPU, GPU, power, temperatures, processes.

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

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

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

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

Your personal context engine for macOS, with Windows and Linux in alpha: on-device meeting notes, screen recall, dictation, and autocomplete

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KV

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

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。

Native macOS video editor that coding agents can drive: everything the UI does, Claude Code and Codex can do through the bashcut CLI or MCP

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

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

🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs).

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

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

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memo

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

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

A smarter subtitle studio powered by advanced ASR models. Refine transcripts with AI and custom glossaries, build bilingual subtitles, and e

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

Big models. Small Macs. Zero excuses.

Turn one machine into a private ChatGPT for a whole room. One command sets up Ollama, Open WebUI, RAG and an OpenAI-compatible API sized to

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

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

Iris-3B pixel-space text-to-image on Apple Silicon GPUs: Metal-optimized engine, native macOS app, CLI, Python and local HTTP API

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

Apple TV Siri Remote for Mac — remote control your Mac with the Apple TV Remote: buttons, trackpad, presentation clicker, and voice control.

TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out of

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

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

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

Dictation that runs on your own computer. Press a key, speak, and the text lands in the app you are using. Free and open source, for macOS,