AI 开源项目榜。

Hyper-parameter optimization for sklearn

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

General code to convert a trained keras model into an inference tensorflow model

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

Homomorphic machine learning

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

Adala: Autonomous DAta (Labeling) Agent framework

Machine Learning for Algorithmic Trading, Second Edition - published by Packt

The Self-Coding System for Your App — Alan AI SDK for Ionic

The basic distribution probability Tutorial for Deep Learning Researchers

Meta-Transformer for Unified Multimodal Learning

MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Protocol）+ ADK（Agent Development Kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

A fast and lightweight framework for creating decentralized agents with ease.

Generate images from texts. In Russian

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

Database Reporting Tool and Tasks (.Net)

Awesome resources on normalizing flows.

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

A Python package that makes it easy for developers to create AI apps powered by various AI providers.

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.

Hyperparameter Experiments with TensorFlow and Keras

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

This is a very early attempt at having chatGPT work within a telegram bot

⚡ Langchain apps in production using Jina & FastAPI