Important
Star and Contribute, let's make community of robotics better and better! π₯
A curated collection of utilities for LeRobot Projects, including data conversion scripts, preprocessing tools, training workflow helpers and etc..
- [2025.10.04] We have collected and updated all Dataset Version Conversion Scripts for LeRobot! π₯π₯π₯
- [2025.09.28] We have upgraded LeRobotDataset from v2.1 to v3.0! π₯π₯π₯
- [2025.06.27] We have supported Data Conversion from LIBERO to LeRobot! π₯π₯π₯
- [2025.05.16] We have supported Data Conversion from LeRobot to RLDS! π₯π₯π₯
- [2025.05.12] We have supported Data Conversion from RoboMIND to LeRobot! π₯π₯π₯
More News
- [2025.04.15] We add Dataset Merging Tool for merging multi-source lerobot datasets! π₯π₯π₯
- [2025.04.14] We have supported Data Conversion from AgiBotWorld to LeRobot! π₯π₯π₯
- [2025.04.11] We change the repo from
openx2lerobottoany4lerobot, making a ββuniversal toolbox for LeRobotββ! π₯π₯π₯ - [2025.02.19] We have supported Data Conversion from Open X-Embodiment to LeRobot! π₯π₯π₯
-
Dataset Tutorial:
- Dataset Loading
- Dataset Editing
- Dataset Filtering
- Dataset Sampling
- Dataset Merging
-
ββData Conversionββ:
-
Training:
- MultiLeRobotDataset
-
EO1: An Open Unified Embodied Foundation Model for General Robot Control Trained on Interleaved Vision-Text-Action Data
-
Hume: A Dual-System VLA with System2 Thinking
-
OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
-
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
-
SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes
-
openpi: the official implemenation of
$Ο_0$ : A Vision-Language-Action Flow Model for General Robot Control -
Isaac-GR00T: NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills
- Official: State-of-the-art Machine Learning for real-world robotics.
- IPEC-COMMUNITY/OpenX: Open X-Embodiment datasets in LeRobot format with standard transfomation
- IPEC-COMMUNITY/LIBERO: LIBERO datasets in LeRobot format with standard transfomation and filtering
- weijian-sun/agibotworld-lerobot: AgibotWorld-LeRobot v2.0
- GR00T-Dateset: Isaac-GR00T training dataset
- nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim: Isaac-GR00T training dataset
- RoboCOIN/robocoin: An open-source bimanual robot manipulation dataset
- behavior-1k/2025-challenge-demos: BEHAVIOR Challenge dataset
- unitree_IL_lerobot: a training framework enabling the training and testing of data collected using Unitree's G1 robot
- Dora-LeRobot: Lerobot boosted with dora
- Fourier-Lerobot: A training pipeline with Fourier dataset
- Adora-LeRobot: a modified version of lerobot, specifically adapted for the Adora robot
- BiLerobot: A bimanual robotics platform combining LeRobot and ManiSkill for advanced dual-arm manipulation tasks using the SO100 robot digital twin
- lerobot-piper: About Use Lerobot to collect piper robot arm data, and perform training and reasoning
- Lerobot-koch: LeRobot Training Notes for Koch Arm
- LeFranX: Franka and XHand Extension for LeRobot
- U-Arm: Lerobot-Everything-Cross-Embodiment-Teleoperation
- lerobot-robot-xarm: xArm integration for LeRobot
- LeKiwi: Low-Cost Mobile Manipulator
- XLeRobot: Fully Autonomous Household Dual-Arm Mobile Robot for $998
- LeRobot-Kinematics: Simple and Accurate Forward and Inverse Kinematics Examples for the Lerobot SO100 ARM
- lerobotdepot: a reoi for hardware, components, and 3D-printable projects compatible with the LeRobot library
- PingTi-Arm: A human-scale robotic arm compatible with Lerobot, based on SO100
- LeDog: A mobile manipulator with a Weilan AlphaDog and a LeRobot-compatible SO-101 arm, with support for ROS 1/2 (Official: ledog_ros2)
- Official Docs: This tutorial will explain how to train a neural network to control a real robot autonomously.
- YouTube: LeRobot Tutorials
- Robotics Course: A course on robotics by Hugging Face using LeRobot
- LeRobot Tutorial with MuJoCo: Examples for collecting data and training with MuJoCo
- LeRobot Sim2Real: Train in fast simulation and deploy visual policies zero shot to the real world
- lerobot-hilserl-guide: Guide and tutorial to run the HILSerl implementation of LeRobot
- LeRobotTutorial-CN: a tutorial for LeRobot in Chinese
- PathOn.AI: Learn Robotics at PathOn.AI is a platform for learning robotics and AI
- NVIDIA Jetson Tutorials
- lerobot_ws: ROS 2 Package for LeRobot SO-ARM101
- lerobot-ros: Running LeRobot and ROS 2 on custom LIDAR
- Physical AI Tools: Physical AI Development Interface with LeRobot and ROS 2
- LeRobot.js: interact with your robot in JS, inspired by LeRobot
- LeLab: A web UI interface on top of lerobot
- LeRobot Episode Scoring Toolkit: One-click tool to score, filter, and export higher-quality LeRobot datasets
- LERO: LeRobot dataset operations toolkit
- LeRobot Dataset Visualizer: Web application for visualizing robotics datasets in LeRobot format
- lerobot_so101_teleop: Sample Environment for the LeRobot SO-101 Robot in Isaac Lab to collect demonstrations in a simulation
- Robot Learning: A Tutorial: All the source code for "Robot Learning: A Tutorial". Get involved to be featured in the next iteration
- LERO: LeRobot dataset Operations toolkit
- CRISP: Record datasets and deploy policies using LeRobot and ROS2-compatible manipulators (Franka Robotics FR3 and more supported)
We appreciate all contributions to improving Any4LeRobot!
This project is released under the MIT License.
If you find this repository helpful in your research or projects, please consider citing it:
@misc{any4lerobot,
title = {Any4LeRobot: A tool collection for LeRobot},
author = {Qizhi Chen},
license = {MIT},
url = {https://github.com/Tavish9/any4lerobot},
year = {2025},
}
@article{eo1,
title={EO-1: Interleaved Vision-Text-Action Pretraining for General Robot Control},
author={Delin Qu and Haoming Song and Qizhi Chen and Zhaoqing Chen and Xianqiang Gao and Xinyi Ye and Qi Lv and Modi Shi and Guanghui Ren and Cheng Ruan and Maoqing Yao and Haoran Yang and Jiacheng Bao and Bin Zhao and Dong Wang},
journal={arXiv preprint},
year={2025},
url={https://arxiv.org/abs/2508.21112}
}