Skip to content

OpenCyberGlove: An Open-source Data Glove for Embodied AI

Discord Notion Website
GitHub stars License

OpenCyberGlove

The OpenCyberGlove is an open-source high fidelity finger tracking glove. We aim to contribute to research on robotic dexterous hands by providing efficient hand motion tracking, accelerating the development of robotic dexterous manipulation.

Key Features

  • 🪶 Super light and thin, 25g for each glove
  • 📐 High DoF, with 19 flex sensors integrated
  • ✅ High accuracy, data-driven method joint angle estimation
  • 📻 High frequency, up to 120 Hz
  • 🎮 Plug and play, full-stack open-source SDK and examples
  • 💰 Cost efficient, cheaper than most hand motion capture solutions

For more glove information and demo video, please check out product introduction page.

Documentation

Get Started

  • User Guide: Please read this guide carefully before playing with the gloves
  • Software: Detailed software installation and configuration instructions

Reference

Change Log

  • 2025-07: OpenCyberGlove🧤 is now available.

Citation

If you use OpenCyberGlove in your research, please cite our work:

@misc{opencyberglove2025,
  author = {CyberOrigin.ai},
  title = {OpenCyberGlove: An Open-source Data Glove for Embodied AI},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/CyberOrigin2077/open_cyber_glove}
}

Contributing

We welcome contributions! Please see our Contributing Guidelines for details on how to submit pull requests, report issues, and suggest improvements.

License

This project is licensed under the BSD 3-Clause License - see the license file for details.

Contact