AI 开源项目榜。

PyTorch implementation of Deformable Convolution

⚡ Self-hostable YesCaptcha-compatible captcha solver built with FastAPI, Playwright, and OpenAI-compatible multimodal models.

TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

马良写作 AINoval — AI novel writer for Chinese webnovels（网文）| 多智能体AI小说创作平台：三级大纲、知识图谱一致性、30万字连载

Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods.

This project analyzes Tennis players in a video to measure their speed, ball shot speed and number of shots. This project will detect players and the tennis ball using YOLO and also utilizes CNNs to extract court keypoints. This hands on project is perfect for polishing your machine learning, and computer vision skills.

Point cloud registration pipeline for robot localization and 3D perception

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

A suite of test scenarios for multi-agent reinforcement learning.

Implementation of Transformer model (originally from Attention is All You Need) applied to Time Series.

🧠+🎧 Build your music algorithms and AI models with the next-gen DAW 🔥

SFrame: Scalable tabular and graph data-structures built for out-of-core data analysis and machine learning.

A playbook for effectively prompting post-trained LLMs

A production-ready template to kickstart your Generative AI projects with structure and scalability in mind.

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

침착한 생성모델 학습기

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

Examples of prompts for Microsoft Copilot

RNNLIB is a recurrent neural network library for sequence learning problems. Forked from Alex Graves work http://sourceforge.net/projects/rnnl/

Standalone TFRecord reader/writer with PyTorch data loaders

PDF to markdown using vision LLMs — tables, layouts, and structure preserved

Pytorch implementation of FlowNet by Dosovitskiy et al.

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

Graph-based LLM power tool for exploring many completions in parallel.