AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

A feature-rich command-line audio/video downloader

Deep Learning for humans

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

⚡ A Fast, Extensible Progress Bar for Python and CLI

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Image-to-Image Translation in PyTorch

Convert PDF to markdown + JSON quickly with high accuracy

Code for the paper "Language Models are Unsupervised Multitask Learners"

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Issues found on WSL

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

OCR, layout analysis, reading order, table recognition in 90+ languages

Datasets, Transforms and Models specific to Computer Vision

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

OpenSnitch is a GNU/Linux interactive application firewall inspired by Little Snitch.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

MVT (Mobile Verification Toolkit) helps with conducting forensics of mobile devices in order to find signs of a potential compromise.

High-Resolution 3D Human Digitization from A Single Image.

Running large language models on a single GPU for throughput-oriented scenarios.

Wan: Open and Advanced Large-Scale Video Generative Models

Fully automated homelab from empty disk to running services with a single command.

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Pythonic AI generation of images and videos

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

tensorboard for pytorch (and chainer, mxnet, numpy, ...)