huggingface/lerobot

Analysis updated 2026-06-21

★ 23,781PythonAudience · researcherComplexity · 4/5Setup · hard

Mindmap

mindmap
  root((LeRobot))
    What it does
      Robot control
      Dataset storage
      AI policy training
    Hardware support
      Hobby arms
      Humanoid robots
    Tech stack
      Python
      PyTorch
    Use cases
      Imitation learning
      Benchmarking
      Data sharing

mindmap root((LeRobot)) What it does Robot control Dataset storage AI policy training Hardware support Hobby arms Humanoid robots Tech stack Python PyTorch Use cases Imitation learning Benchmarking Data sharing

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Train a robot arm to pick up objects by recording human demonstrations and running imitation learning

USE CASE 2

Share standardized robot demonstration datasets with other researchers using the LeRobotDataset format

USE CASE 3

Fine-tune a vision-language-action model to respond to natural language commands on your own robot hardware

USE CASE 4

Run LIBERO benchmarks to compare two AI policies on a standard task

What is it built with?

PythonPyTorch

How does it compare?

	huggingface/lerobot	pyg-team/pytorch_geometric	delgan/loguru
Stars	23,781	23,722	23,852
Language	Python	Python	Python
Setup difficulty	hard	moderate	easy
Complexity	4/5	3/5	1/5
Audience	researcher	researcher	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1day+

Requires physical robot hardware and a GPU-capable machine with PyTorch for training AI policies.

In plain English

LeRobot is an open-source Python library from Hugging Face that makes it easier for researchers and hobbyists to build AI-powered robots. The problem it solves is that robotics research is fragmented: different robots speak different languages, datasets are stored in incompatible formats, and training AI models from scratch requires deep expertise. LeRobot provides a common platform that ties all of this together. At its core, the library offers three things. First, a unified programming interface for controlling robots, whether that is a cheap hobby arm like the SO-100 or a full humanoid like Reachy2, the same Python code works across all supported hardware. Second, a standardized dataset format called LeRobotDataset that stores synchronized video footage and sensor readings so that thousands of recorded robot sessions can be shared, streamed, and reused. Third, a collection of ready-to-use AI policies, meaning the decision-making brains you slot into a robot. These range from simple imitation learning (the robot copies human demonstrations) to advanced Vision-Language-Action models that understand natural language commands. You would use LeRobot if you want to train a robot arm to pick up objects, share robot demonstration data with other researchers, fine-tune an existing AI policy on your own hardware, or run standard benchmarks like LIBERO to compare your models. It is aimed at anyone who finds robotics interesting but does not want to rebuild all the plumbing from scratch. The tech stack is Python and PyTorch.

Copy-paste prompts

Prompt 1

Using LeRobot, show me how to record a dataset of my SO-100 robot arm picking up objects and then train an imitation learning policy on it.

Prompt 2

I have LeRobot installed and a compatible robot arm connected. Write a Python script that loads a pre-trained policy and runs it on the robot.

Prompt 3

Explain how LeRobotDataset stores synchronized video footage and sensor readings, and show me how to load and inspect an existing dataset from Hugging Face Hub.

Prompt 4

How do I run LIBERO benchmarks with LeRobot to compare the performance of two different AI policies on the same task?

Prompt 5

Show me how to use a Vision-Language-Action model from LeRobot to make a robot respond to a natural language command like 'pick up the red block'.

Frequently asked questions

What is lerobot?

An open-source Python library from Hugging Face that gives researchers and hobbyists a common platform to control robots, collect training data, and run AI decision-making models, without rebuilding incompatible plumbing for each robot.

What language is lerobot written in?

Mainly Python. The stack also includes Python, PyTorch.

How hard is lerobot to set up?

Setup difficulty is rated hard, with roughly 1day+ to a first successful run.

Who is lerobot for?

Mainly researcher.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub huggingface on gitmyhub

Verify against the repo before relying on details.