Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Govee2MQTT: Connect Govee lights and devices to Home Assistant

Unofficial API for YouTube Music

The spatial IDE for recursive multi-agent orchestration.

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Sketchup Model Context Protocol

MCP server for controlling ThreeJs source code, only basic function

An MCP (Model Context Protocol) server that enables AI agents to inspect and manipulate Three.js/Threlte scenes in real-time.

AudioMuse-AI is an Open Source Dockerized environment that brings automatic playlist generation to Jellyfin, Navidrome, LMS, Lyrion and Emby. Using powerful tools like Librosa and ONNX, it performs…

Review Your Music of 2025. A "Spotify Wrapped"-like app made for people who use Jellyfin for listening to music!

Apple Music metadata provider for Jellyfin

A cross-platform, free and open source music player for Jellyfin, powered by React Native

A Subsonic API proxy server that focuses on integrating SquidWTF as an external music source for Navidrome.

macOS System-wide Audio Equalizer & Volume Mixer 🎧

Port of OpenAI's Whisper model in C/C++

Keep track of used ports

https://hf.co/hexgrad/Kokoro-82M

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code and OpenCode.

Prompts, workflows and more for agentic engineering

This repository contains my personal configuration settings for Claude Code, Anthropic's official CLI tool for coding.

nw_wrld is an event-driven sequencer for triggering visuals using web technologies. It enables users to scale up audiovisual compositions for prototyping, demos, exhibitions, and live performances.…

The Clojure programming language

Access your entire server infrastructure from your local desktop

Window management made elegant.

A macOS app for customizing which browser to start

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.