AI open source rankings.

Voice & Video Calling and Text Chat App for Flutter

⚡ Insanely fast AI voice assistant with <500ms response times

Comfyui多功能聚合插件（提示词翻译，提示词润色，贴图编辑器，模型引用修复等），让comfyui任意长文本输入框支持中文输入并自动翻译/同时加入报错翻译功能（调用百度翻译），实现翻译自由！同时接入AI大模型实现提示词润色功能， 其它插件功能，请看插件介绍

PyTorch Re-Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349

Repository of best practices for deep learning in Julia, inspired by fastai

Vision Transformers for Single Image Dehazing

Fixes AI pixel art images, video, or sprite web uploads

A minimal, distraction-free markdown editor built with Tauri, React, and TypeScript

[ICLR 2026] Streamlining Cartoon Production with Generative Post-Keyframing

High-performance MLX-based LLM inference engine for macOS with native Swift implementation

MCP Server for YouTube API, enabling video management, Shorts creation, and advanced analytics

Convolutional Neural Networks for Sentence Classification in Keras

unofficial implementation of Comfyui magic clothing

pytorch version of spatial transformer networks

A Tutorial on Manipulator Differential Kinematics

Diffusers wrapper to run Kwai-Kolors model

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the house - with AirPlay-grade audio in every room, all in sync.

Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).

A platform for building conversational interfaces with intelligent agents (chatbots)

🔍 Explore what happens under the hood with the ChatGPT web app, its backend API calls and more. And some speculation, of course.

Tactile: an accessibility-first operating layer for agents.

A plug-and-play deploy framework for robots. Just deploy, just do.

Destruction and Construction Learning for Fine-grained Image Recognition

A python library for social event detection

CL-bench: A Benchmark for Context Learning

Native macOS SwiftUI app for managing multiple AI code agent skills

Let AI Drive Unity, from Editor to Play Mode.

A collection of generative methods implemented with TensorFlow (Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoder (VAE) and DRAW: A Recurrent Neural Network For Image Generation).

한국 법령 기반 개인정보처리방침·이용약관 자동 생성 Claude Code 스킬. 2025.4.21 작성지침 및 2026.3 개정 법령 반영.