AI 开源项目榜。

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose

Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.

This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.

Monthly Series - Machine Learning Top 10 Open Source Projects

VibeCurb - Injects taste into AI workflows to stop agents from generating boring, AI slop.

Flight code for MIT CSAIL Robot Locomotion Group flying-through-forests project

AI agent for building React Native apps

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.

Implementation of popular ML algorithms from scratch

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

:tiger: Sara - the Rasa Demo Bot: An example of a contextual AI assistant built with the open source Rasa Stack

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.

Dynamic seq2seq in TensorFlow, step by step

Deep Image Matting

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Input pipeline framework

Implementations of a number of generative models in Tensorflow 2. GAN, VAE, Seq2Seq, VAEGAN, GAIA, Spectrogram Inversion. Everything is self contained in a jupyter notebook for easy export to colab.

Pytorch implementation of Center Loss

Awesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code

A PyTorch Implementation of Focal Loss.

A demo of an GPT-based agent existing in an RPG-like environment

[Book-2021] Practical MLOps O'Reilly Book

An implementation of the Nvidia's Parakeet models for Apple Silicon using MLX.

[ICLR 2026] Streaming 4D Visual Geometry Transformer

企业级稳定的OpenAI、Claude、Gemini等的API接口-For企业和开发者。OpenAI的api proxy，支持ChatGPT的API调用，支持Anthropic claude的官方接口形式，支持Google gemini的官方接口形式，支持：gpt-5，sora。不需要openai Key, 不需要买openai的账号，不需要美元的银行卡，通通不用的，直接调用就行，稳定好用！！智增增

GPT RStudio addins that enable GPT assisted coding, writing & analysis