peridyno/peridyno

An AI-targeted physical simulation platform.

What it solves

PeriDyno provides a high-performance physics engine designed to create real-time physical environments for intelligent agents to operate within.

How it works

It is a highly parallel physics engine built using CUDA, with optional support for Vulkan. This allows it to leverage GPU acceleration to handle complex simulations efficiently.

Who it’s for

Developers building intelligent agents that require realistic, real-time physical simulation environments.

Highlights

  • CUDA-based parallel processing for high speed.
  • Support for multiple application interfaces, including GLFW, Qt, and web applications, without requiring code changes.
  • Optional Vulkan support for graphics and simulation.

Related

  • Project
    TNY-Robotics/TNY-360

    An open-source quadruped robot dog featuring a dual-core ESP32-S3 architecture and closed-loop servo control for precise movement and interaction.

  • Project
    Phyzicalorg/Phyzical_org

    A browser-based robot teleoperation platform that crowdsources human demonstration data for training Vision-Language-Action (VLA) models and imitation learning policies.

  • Project
    OpenMOSS/EasyWAM

    EasyWAM is an open‑source, modular codebase for training and evaluating World Action Models (robotic video‑action predictors). It supports multiple backbones, LoRA fine‑tuning, FlashAttention, DeepSpeed, and provides ready‑to‑run recipes for benchmarks such as LIBERO, RoboDojo, and RoboCasa365.

  • Project
    jolibrain/colette

    Colette is a self‑hosted RAG platform that indexes PDFs as images, preserving tables, figures and layout. It combines vision embeddings, BM25 lexical search, and optional HyDE prompting, and runs on high‑end GPUs via Docker. Ideal for confidential technical documentation.