AI 开源项目榜。

CRNN (CNN+RNN) for OCR using Keras / License Plate Recognition

:octocat: A curated awesome list of AI Startups in India & Machine Learning Interview Guide. Feel free to contribute!

Python + Inference - Model Deployment library in Python. Simplest model inference server ever.

Lip and hair color editor using face parsing maps.

Here are the Top 100 prompts on GPTStore, which we can use to learn and improve prompt engineering.

The official PyTorch implementation of L2CS-Net for gaze estimation and tracking

Open Source Library for GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android

Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "把影视生成的执行图从拓扑序变成关键路径最优调度" ; 唯一把场景叙事依赖建模为 DAG、以 CPM 算法驱动并行调度的影视生成引擎

macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.

Pytorch Implementation of: "Stable-Hair: Real-World Hair Transfer via Diffusion Model" (AAAI 2025)

TensorFlow Lite Flutter Plugin

Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"

Neural network-based chess engine capable of natural language commentary

🌊 Numerically solving and backpropagating through the wave equation

Get started with native image generation and editing using Gemini 2.0 and Next.js

Implementation of paper "Towards a Unified View of Parameter-Efficient Transfer Learning" (ICLR 2022)

Keras library for building (Universal) Transformers, facilitating BERT and GPT models

A set of tools to use in Microsoft Azure Form Recognizer and OCR services.

A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph.

"A neural algorithm of Artistic style" in tensorflow

🧠 NeuroConscious Transformer (NCT) - A next-generation neuromorphic consciousness architecture integrating Transformer with Global Workspace Theory, Predictive Coding, and IIT. | 下一代神经形态意识架构，融合Transformer与全局工作空间、预测编码、整合信息理论。

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Codex/Claude Code/Cursor的开源增强版，专注一句话实现复杂长程任务（教育、编程、办公、生活、娱乐、游戏）。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSeek 等国产大模型。技能/插件/跨会话记忆，8 层安全沙箱，数据不离开你的机器。Docker 一键部署，MIT 开源，零锁定。

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

This is an official implementation for "Contextual Transformer Networks for Visual Recognition".

[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

One-click Portable Windows installation of 'AI-Toolkit by Ostris'

Official Code Repo for UniVA: Universal Video Agents

Repository for scripts and notebooks from the book: Programming PyTorch for Deep Learning

🔥 Generate llms.txt and llms-full.txt files for any website!