AI 开源项目榜。

Synthetic Data SDK ✨

An AI agent that can get things done across iPhone apps.

Full-stack open-source interactive long-horizon world model.

Using the genetic algorithm and neural networks I trained up 5 snakes who will then fuse to become the ultimate snake, this is how I did it

Building DeepSeek R1 from Scratch

A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019).

Diffusion attentive attribution maps for interpreting Stable Diffusion.

A dataset of datasets for learning to learn from few examples

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

使用vercel的functions，将ai功能加入微信公众号

🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.

Deep Learning Illustrated (2020)

Solidity Static Analyzer that easily integrates into your editor

LLM4AD: A Platform for Algorithm Design with Large Language Model

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and action-conditioned video, as well as planning using JEPA-based models.

Deep Reinforcement Learning with pytorch & visdom

Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across documents — knowledge that persists and compounds, for you and your AI agents. All from the CLI.

Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..

Tabular Deep Learning Library for PyTorch

An agent supervisor and software factory foreman powered by decision models

基于chatgpt-next-web，增加了midjourney绘画功能，支持mj-plus的ai换脸和局部重绘，接入了stable-diffusion，支持oss，支持接入fastgpt知识库，支持suno，支持luma。支持dall-e-3、gpt-4-vision-preview、whisper、tts等多模态模型，支持gpt-4-all，支持GPTs商店。新增加了支持后台管理的版本，包括登录注册，平台模型apikey管理，套餐管理，消息保存等。

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

DaC is a dashboard-as-code tool. Build interactive dashboards using YAML and JSX. Built-in semantic layer. Get your agents to build standardized, reviewable dashboards.

MADGRAD Optimization Method

Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

Claude Code, rewritten from scratch in Go. Zero Node.js. Zero Electron. One binary.

Lightweight & fast OCR models for license plate text recognition.

Fast, streaming indexing, query, and agentic LLM applications in Rust