AI 开源项目榜。

unofficial vits2-TTS implementation in pytorch

iOS client for coding agents via ACP or Codex app-server

PyTorch implementation of some attentions for Deep Learning Researchers.

Go Wechaty is a Conversational SDK for Chatbot Makers Written in Go

[ICLR'26] Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.

An easy to understand and better performance version of CenterNet

Claw Code No Rust No TypeScript Only Python. Easy to work with. Fast to iterate. 🔥 Zero external dependencies 🔥

The User Pays AI SDK

Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon.

Efficient 6-DoF Grasp Generation in Cluttered Scenes

Comprehensive Deep Learning Tutorial : From Zero To Hero

GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models

Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.

Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022

"Aurogen🍊: The Multi-Agent Evolution of OpenClaw."

[CVPR 2020] Meshed-Memory Transformer for Image Captioning

Extract hardcoded subtitles from videos using machine learning

Awesome machine learning model compression research papers, quantization, tools, and learning material.

Doodle AR masks right from the browser with tensorflow.js

🚀 😏 Near Real Time CPU Face detection using deep learning

预训练语言模型综述

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

macOS 上的 Codex、Claude Code CLI 与 Claude Desktop 多实例管理器，统一管理账号、供应商密钥、独立配置、会话与代理。 / A macOS manager for Codex, Claude Code CLI and Claude Desktop instances, accounts, provider keys, isolated configs, sessions and proxies.

Your AI friend right in your browser

Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team.

Extension of Wav2Lip repository for processing high-quality videos.