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.

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

OpenDAN is an open source Personal AI OS , which consolidates various AI modules in one place for your personal use.

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

a reimplementation of PWC-Net in PyTorch that matches the official Caffe version

Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

Xircuits toolkit for creating and experimenting with BabyAGI/AutoGPT-style agents

Keeping language models honest by directly eliciting knowledge encoded in their activations.

This tool allows you to easily convert any image into a 3D print-ready STL model. The surface of the model will display the image when illuminated from the left side.

AutoGPT prompt template for file based instructions and advice

AutoGPT with commands, read/write/del access. Edit .env file for working changes

3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising (TNNLS 2020)

PyTorch implementation of "Deep Plug-and-Play Prior for Hyperspectral Image Restoration" (Neurocomputing 2022)

3D micro-world generator for evaluating AI systems

Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance (TNNLS 2023)

Hyperspectral Image Denoising with Realistic Data

Torchlight is a light-weight PyTorch wrapper with many useful util functions for fast prototyping of computer vision models.

The project is a novel approach to generate 3D buildings with semantics (here doors, windows). Machine learning model using decision tree and random forest is used to detect the semantics and then …

This project is prepared for converting your 3D model dataset to a multi-view dataset

A Blender Addon that can generate and export 3D models of individual text characters

An exploitation framework written for curious reasons

Unofficial implementation of CrossNet and CrossNet++.

A GUI for Video2X written in Python with Qt 6

‘Generative House Algorithm’ was constructed for one simple reason, being one click away from creating a range of uniquely designed model houses. At the beginning of 2020, the start of the covid-19…

Engine for randomly generating 3D building models.