Integrate cutting-edge LLM technology quickly and easily into your apps

We write your reusable computer vision tools. 💜

Cross-platform, customizable ML solutions for live and streaming media.

High-performance, scalable time-series database designed for Industrial IoT (IIoT) scenarios

🍺 The missing package manager for macOS (or Linux)

🐍 Geometric Computer Vision Library for Spatial AI

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

PyTorch code and models for the DINOv2 self-supervised learning method.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

A C++ Background Subtraction Library with wrappers for Python, MATLAB, Java and GUI on QT

A collaboration friendly studio for NeRFs

Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024

Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

LLM training in simple, raw C/CUDA

Fix every runtime bug on macOS.

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

A comprehensive tool for processing and analyzing video footage, producing detailed insights into gameplay and player performance enhancing game understanding and performance evaluation.

Painter & SegGPT Series: Vision Foundation Models from BAAI

Official ECCV 2022 repository for SUPR: A Sparse Unified Part-Based Human Representation

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

HumanML3D: A large and diverse 3d human motion-language dataset.

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

[CVPR2024, Highlight] Official code for DragDiffusion

Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.

Learning Convolutional Neural Networks with Interactive Visualization.

Doctor Dignity is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.

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

BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability