PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.

Ready-to-use Multilingual Text-To-Speech (TTS) package.

sharing current agents in use

An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

TTS support with GGML

Running any GGUF SLMs/LLMs locally, on-device in Android

Let AI live in small world by using LangChain

macOS comic viewer

The official Python SDK for Model Context Protocol servers and clients

🚀 The fast, Pythonic way to build MCP servers and clients

An MCP server that allows MCP clients like Claude Desktop or Cursor to perform actions in the Unity Editor

This is a small set of cute stylised low-poly game assets to make a cozy little bathroom with.

PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.

Swift Vector Database. On-device, local vector database for building the next-generation of user experiences

Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

🚀 LangChain for Swift. Optimized for iOS, macOS, watchOS (part) and visionOS.(beta)

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

☕ 모각코하기 좋은 국내 카페 리스트

Korean Multi-task Instruction Tuning

A Toon Shader in Unity Universal Render Pipeline.

A simple water shader for Unity URP

A curated list of video stabilization methods

This project contains a collection of Custom Renderer examples. This will be updated as we refine the feature and add more options.

lightweight, standalone C++ inference engine for Google's Gemma models.