irom-princeton/open-world

stars

commits

Python

primary language

Jul 30, 2026

updated

README

🌐 open-world

OpenWorld is an open-source platform for building, fine-tuning, and evaluating robotic policies using video world models. We offer support for various world model families and robot platforms - see MODELS.md for details.

Installation

Requirements:

Python 3.11+
uv for environment management

# Dependencies for base environment only:
uv sync

# Include extra dependencies for using different policies/reward models. Example:
uv sync --extra policy-dp --extra reward-robometer
uv sync --extra policy-openpi --extra reward-robometer

Finally, install required assets for the base world model:

sudo apt-get install git-lfs -y
bash external/download_models.sh

Supported Workflows

	bidirectional-svd	AR-wan	AR-cosmos
🏋️ Training
World Model Training	✅	✅	❌ TODO
Policy Training	✅	✅	✅
✨ Inference
Trajectory Replay	✅	✅	❌ TODO
Policy Evaluation	✅	✅	❌ TODO
Teleoperation	❌ TODO	✅	❌ TODO

Acknowledgements

This repo is based on Ctrl-World, dppo, dsrl, openpi, and robometer.

Contributors

tenny-yinyijun

74 commits

jmsceats

1 commits

Similar repos

OpenDCAI/OpenWorldLib

Unified Codebase for Advanced World Models.

870

galilai-group/stable-worldmodel

A platform for reproducible world model research and evaluation

2,183

WwZzz/VLAStudio

Imitation Learning; Robotics; Policy; VLA;

open-gigaai/giga-world-1

A Roadmap to Build World Models for Robot Policy Evaluation

1,154

Physical-Intelligence/openpi

13,685

airman-and/TwinVLA

WeikeShi0730/lerobot_on_track

huggingface/lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

27,360

Languages

Python

97.5%

Shell

2.5%

irom-princeton/open-world

stars

commits

Python

primary language

Jul 30, 2026

updated

README

🌐 open-world

Installation

Requirements:

Python 3.11+
uv for environment management

# Dependencies for base environment only:
uv sync

# Include extra dependencies for using different policies/reward models. Example:
uv sync --extra policy-dp --extra reward-robometer
uv sync --extra policy-openpi --extra reward-robometer

Finally, install required assets for the base world model:

sudo apt-get install git-lfs -y
bash external/download_models.sh

Supported Workflows

	bidirectional-svd	AR-wan	AR-cosmos
🏋️ Training
World Model Training	✅	✅	❌ TODO
Policy Training	✅	✅	✅
✨ Inference
Trajectory Replay	✅	✅	❌ TODO
Policy Evaluation	✅	✅	❌ TODO
Teleoperation	❌ TODO	✅	❌ TODO

Acknowledgements

This repo is based on Ctrl-World, dppo, dsrl, openpi, and robometer.

Similar repos

OpenDCAI/OpenWorldLib

Unified Codebase for Advanced World Models.

870

galilai-group/stable-worldmodel

A platform for reproducible world model research and evaluation

2,183

WwZzz/VLAStudio

Imitation Learning; Robotics; Policy; VLA;

open-gigaai/giga-world-1

A Roadmap to Build World Models for Robot Policy Evaluation

1,154

Physical-Intelligence/openpi

13,685

airman-and/TwinVLA

WeikeShi0730/lerobot_on_track

huggingface/lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

27,360

Contributors

tenny-yinyijun

74 commits

jmsceats

1 commits

Languages

Python

97.5%

Shell

2.5%