Lists (5)
Starred repositories
An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.
💌 A beautiful, fast and fully open source mail client for Mac, Windows and Linux.
A Collection of application ideas which can be used to improve your coding skills.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Rules and Knowledge to work better with agents such as Claude Code or Cursor
A collaborative list of awesome Swift libraries and resources. Feel free to contribute!
Audio synthesis, processing, & analysis platform for iOS, macOS and tvOS
Largest list of models for Core ML (for iOS 11+)
📊 Path to a free self-taught education in Data Science!
macOS app that can gradually increase/tweak the Night Shift warmth intensity at set times, so you could make your screen warmer as you go further into the night. Does not run in the background - us…
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.…
Create a good-looking DMG for your macOS app in seconds
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
🎓 Path to a free self-taught education in Computer Science!
llama and other large language models on iOS and MacOS offline using GGML library.
Bootstrap apps to get you started building AI apps with AIProxy
An invoice generator app built using Next.js, Typescript, and Shadcn
🔊 Text-Prompted Generative Audio Model
Lightweight, flexible HTTP server framework written in Swift
SwiftSoup: Pure Swift HTML Parser, with best of DOM, CSS, and jquery (Supports Linux, iOS, Mac, tvOS, watchOS)
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)