AI open source rankings.

GIT: A Generative Image-to-text Transformer for Vision and Language

A living space where people and agents create, play, and build together.

Open-Source Reproduction/Demo of the LLM Riddles Game

PyTorch and Tensorflow functional model definitions

Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"

The project is an official implementation of our paper "3D Human Pose Estimation with Spatial and Temporal Transformers".

lowfat - slim your command output. strips noise, saves tokens.

Codex 皮肤生成器（内置沉浸式女友、复古 QQ 风格）

🎯 A comprehensive gradient-free optimization framework written in Python

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

Rotational region detection based on Faster-RCNN.

A desktop application that extracts YouTube playlist transcripts and enhances them using Google's Gemini AI models. The output is a book in any language you want.

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

一份中文综述文章列表（自然语言处理&机器学习）

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

[ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

One local endpoint that routes Claude Code, Cursor, Cline, Aider, Codex CLI and the SDKs through the Claude and ChatGPT plans you already pay for: seats first, then the fallback chain you configure, and a ledger of who paid. Zero runtime dependencies.

:sweat_drops: Seamless, distributed, real-time integration of Blender into PyTorch data pipelines

The easiest way to build and deploy an agent

Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"

Natural Language Processing with Transformers 中译本，最权威Transformers教程

PyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)

😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.

Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.

Este projeto explora a integração do ChatGPT com o WhatsApp, transformando o chatbot em um assistente virtual capaz de realizar tarefas como falar com amigos, responder a perguntas de clientes, e muito mais, com um toque de humanização nas conversas.

A React Native wrapper around ChatGPT to seamlessly integrate it with your applications. It handles authentication, streamed responses, and keeping track of conversations. 100% client-side :robot:

An MCP Multimodal AI Agent with eyes and ears!

Create browser automation as if you were teaching a human using GPT-4 Vision.