Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
Repository Index
47,133 repositories indexed
1–24 of 25 · Most stars
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
Native port of Redis for Windows. Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs. This repository contains unofficial port of Redis to Windows.
- redis
- redis-windows
- redis-windows-native
- redis-windows-installer
Translated青简 Qingjian ("green bamboo slips"): a pinyin input method written in Rust, with an extra translated word in the language you are learning shown next to each candidate word
- chinese
- chinese-input-method
- english-learning
- ime
Turn off Apple Intelligence and delete its models on your Mac. Optional tweaks for analytics, ads and pop-ups. A native app and CLI, and every change can be undone.
JSONExport is a desktop application for Mac OS X which enables you to export JSON objects as model classes with their associated constructors, utility methods, setters and getters in your favorite language.
A local inference engine for Apple silicon, built around the model.
- apple-silicon
- coding-agents
- llm-inference
- macos
A very lightweight but powerful ViewModel-First MVVM framework for WPF for .NET Framework and .NET Core, inspired by Caliburn.Micro.
- stylet
- mvvm
- mvvm-framework
- wpf
macOS app to generate Swift 5 code for models from JSON (with Codeable)
- swift
- json-files
- json-generator
- swift5
Your home as a live 3D model in the Mac menu bar and on iPhone — lights and ACs via Smart Life, Home Assistant, Philips Hue and Apple Home.
Library simplifying the concept of opening dialogs from a view model when using MVVM in WPF
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
- apple-silicon
- llm
- llm-inference
- local-llm
TranslatedFerry OpenCode's free models over to WorkBuddy — isolated runtime, concurrent detection, verdict caching, one-click import, and a local OpenAI-compatible forwarding port
A tool for generating immutable model objects
- swift
- objective-c
- models
- macos
TypeScript SQLite layer with support for both native C++ & pure JavaScript drivers.
Monorepo containing Keadex applications and libraries.
- docusaurus
- microfrontend
- rust
- tauri
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.
- ai-assistant
- apple-silicon
- desktop-app
- fine-tuning
TranslatedA Zhuyin (Bopomofo) input method that needs no character selection: it uses a Transformer locally to choose characters based on the preceding text. Supports Linux (Fcitx5/IBus), macOS, and Windows.
- bopomofo
- chinese-input-method
- fcitx5
- go
Aegis SkinFees: console-grade workspace for CS2 fee math — venue models, FX conversion and net-profit estimates fully on device.
Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — just you and your personal AI assistant
- ai-chat
- artificial-intelligence
- candle
- chatbot
Inferred Model-based Fuzzer
- fuzzer
- kernel-fuzzing
- macos
MacOS app for Generating JSON classes (Template based)
- json
- to
- model
- swift
This repository hosts the specification for the Cartographic Information Model
- specification
- publishing-sharing
- cartography
- desktop
HistoClean is a tool for the preprocessing and augmentation of images used in deep learning models. This easy to use application brings together the most popular image processing packages from across the python universe, meaning no more looking at documentation! HistoClean provides real time feedback to augmentations and preprocessing options. This allows users to evaluate their steps before implementation.
- image-processing
- images
- image-analysis
- deep-learning