A machine learning runtime written in Rust that enables running ONNX models trained in PyTorch and other Python frameworks in Rust and WebAssembly environments.

A collection of example projects and templates demonstrating how to implement AI features like LLMs, computer vision, and simulation in Unity using the Sentis package.

A high-performance inference engine for GPUs and AI accelerators that enables efficient model deployment and academic validation.

A computer vision project that integrates YOLOv7 and YOLOv8 for real-time object detection and tracking across video streams from various sources.

A collection of example projects for self-hosting and deploying various Stable Diffusion family models using the BentoML framework.

A ROS-based development and simulation framework for the xArm series of robotic arms, providing hardware interfaces, MoveIt motion planning, and Gazebo simulation.

Q‑Transformer is a PyTorch library that implements the autoregressive Q‑function approach for scalable offline reinforcement learning, targeting robotic tasks that combine video observations and language instructions. It provides a vision‑transformer model, data‑collection agent, replay‑memory dataset, and Q‑learning trainer, all installable via `pip install q-transformer`.

TFTS is a TensorFlow-based library that provides a unified interface for implementing state-of-the-art deep learning models for time series prediction, classification, and anomaly detection.

A Triton-based subset of PyTorch's nn module that provides a readable and hackable collection of neural network layers for developing custom deep learning operations.

continuous-eval is a Python library for modular, data‑driven evaluation of LLM‑powered pipelines. It provides a catalog of retrieval, generation, code, and agent metrics, lets you attach those metrics to individual pipeline modules, runs them on a dataset, and can enforce regression tests. Custom LLM‑as‑a‑judge metrics are also supported.

Ekho is a Chinese text-to-speech engine that converts written text into spoken audio, supporting custom voice data integration.

A token infilling neural codec language model for high-quality zero-shot text-to-speech and speech editing using only a few seconds of reference audio.

A large-scale multi-view RGB-D dataset of 10,000 indoor scenes designed for training AI models in 3D reconstruction and semantic segmentation.

A whole-body vision-language-action framework for humanoid robots that enables cross-embodiment skill transfer and long-horizon manipulation.

A C++ library for optimization-based inverse-dynamics control of rigid multi-body robots, such as humanoids and quadrupeds.

A comprehensive software stack for the control and simulation of humanoid robots, providing tools for dynamics, perception, and real-time communication.

A Python API for the GraspNet-1Billion dataset, providing tools to load, process, and validate grasp labels and point cloud data for robotic grasping research.

A suite of human-collected datasets and a benchmark for open vocabulary visuolinguomotor learning, enabling robots to execute a vast array of natural language instructions.

An open-source, low-cost electronic speed controller (ESC) for brushless DC motors designed specifically for robotics, supporting FOC and multiple control modes.

A real-time eye gaze and blink estimation system using PyTorch and ROS 2 for tracking gaze direction and blink probability in natural environments.

A flight simulator for rovers, boats, and aircraft using Gazebo plugins to provide SITL and HITL simulation for the PX4 Autopilot.

A low-overhead, real-time control and visualization platform for creating responsive applications that interact with hardware, sensors, and media.

A cross-platform distribution of ROS Noetic that uses the Conda package manager to simplify installation and dependency management across Linux, macOS, and Windows.

A C++ library accompanying the Modern Robotics textbook, providing educational implementations of robotics mechanics, planning, and control algorithms.

A collection of numerically robust and efficient numerical solvers for Linear and Quadratic Programs, designed for high-performance robotics and optimization tasks.

A Rust-based visualizer for URDF and Xacro robot description files that allows interactive joint manipulation and remote control via a JSON API.

YARP is a communication library and toolkit for robotics that provides standardized device interfaces and messaging between software components.

A minimal quadrotor autonomy framework written in Rust that provides real-time dynamics simulation, trajectory planning, and control.

A contribution package for Stable-Baselines3 containing experimental reinforcement learning algorithms and niche tools for researchers and developers.

A collection of URDF loading libraries for Unity and THREE.js that allows developers to import and visualize robot models in 3D environments.

A ROS2 driver for Universal Robots manipulators that enables hardware communication, motion planning via MoveIt2, and integration of ROS2 behaviors into industrial cobots.

A collection of JavaScript client libraries that enable web applications to communicate with ROS (Robot Operating System) systems for building robot interfaces.

A ROS driver for Universal Robots CB3 and e-Series manipulators that provides a stable interface for real-time control, calibration, and integration with ROS-control.

A library for computing time-optimal path parameterization for robots, allowing them to move along a geometric path as quickly as possible while respecting kinematic and dynamic constraints.

A pure-Python library for computing the inverse kinematics of any robot, supporting URDF and MuJoCo MJCF imports and an accelerated JAX backend.

A GPU-accelerated library for rapid 3D data processing in robotics, providing high-performance point cloud algorithms, collision avoidance, and path planning.

A unified platform and benchmark for scalable robot learning that integrates multiple simulation frameworks and datasets into a single interface.

Pixel Reasoner is a research framework that adds visual‑manipulation operations (zoom‑in, select‑frame, etc.) to a Vision‑Language Model, training it via instruction‑tuning and curiosity‑driven reinforcement learning. The repo supplies installation guides, scripts for both SFT and RL stages, pretrained 7 B checkpoints, datasets, and evaluation pipelines for image and video benchmarks.

A local AI tool that automatically generates captions and keywords for images and writes them directly into image metadata for easy indexing and searching.

A universal task router for computer vision that converts a single natural-language instruction into a sequence of specialist model calls to produce images, videos, and 3D models.

MMF is a modular PyTorch-based framework for vision and language multimodal research, providing reference implementations of state-of-the-art models and tools for distributed training.

VLM-FO1 is a plug-and-play module for Vision-Language Models that enhances fine-grained perception and spatial awareness without compromising general reasoning capabilities.

Awesome‑Multimodal‑Modeling is a community‑curated “awesome‑list” that surveys multimodal AI models. It defines four clear families—Traditional, MLLMs, Unified, and Native—explains their architectural differences, and links to open‑source model collections on Hugging Face. The repo serves researchers and engineers who need a structured view of the rapidly evolving multimodal landscape.

A unified open-source framework for evaluating large audio foundation models, supporting both speech understanding and generation across 34 benchmarks.

A native Windows UI for the Whispering Tiger application that enables real-time transcription and translation of audio streams and in-game images.

Kaldi‑Active‑Grammar is a Python wrapper for the Kaldi speech‑recognition engine that lets you compile many small grammars and activate only the needed ones per utterance. It ships binary wheels for all major OSes, includes a pre‑trained English model, and provides a backend for the Dragonfly and Caster voice‑control frameworks. Install via pip, download the model, define rules, and dynamically enable them for context‑aware command‑and‑control.

An OpenAI-compatible API server for running local MLX models on Apple Silicon, supporting text, multimodal, image, and audio models.

A deep learning-based Voice Activity Detection system using a 1D-ResNet and MFCC features to classify audio signals as speech or noise.