#1919th of 26 in ML frameworks and libraries

lerobot

PyTorch library for robot control, datasets and policy training

Live demo ↗ Documentation ↗ Repository on GitHub ↗

Stars: 28k
License: Apache-2.0
Last commit: Oct 2026
Last release: Aug 2026
Language: Python

Missed the latest GitHub check; these facts may be older.

Overview

LeRobot provides a Python Robot interface for arms and humanoids (SO100, Koch, Reachy2, Unitree G1 and others), a Parquet plus MP4 dataset format hosted on the Hugging Face Hub, and PyTorch implementations of imitation learning, RL, VLA, world and reward models. CLI tools cover recording, training and evaluation on benchmarks such as LIBERO and MetaWorld.

Who it is for: Robotics engineers and researchers training policies on real or simulated robots

Strengths

One Robot interface covers many arms, humanoids and teleop devices; plugins auto-discovered by package prefix
LeRobotDataset format streams from the Hub, with tools to split, merge and edit episodes
Many policies in pure PyTorch: ACT, Diffusion, Pi0, SmolVLA, GR00T N1.7, HIL-SERL
One CLI flow for record, train and eval, including simulated benchmarks

Weaknesses

README gives no RAM or VRAM figures; it points to a separate hardware guide
Real-world use needs supported physical hardware; named simulation benchmarks are LIBERO and MetaWorld
Some items, such as QC-FQL, are marked coming soon
Custom robots or policies require implementing the interfaces yourself

What it needs

Docker
Needs PyTorch, Hugging Face Hub
Models: ACT, Diffusion, VQ-BeT, HIL-SERL, TDMPC

Also in ML frameworks and libraries

See all 26

Also in ML frameworks and libraries
Rank	Project	Score
1	transformersPython library defining open models for text, vision, audio and multimodal tasks167.7k starsApache-2.0	94 out of 100
2	pytorchPython tensor library with GPU support and tape-based autograd for deep learning104.7k starscustom license	93 out of 100
3	ultralyticsPython library and CLI for training and running YOLO vision models62.5k starsAGPL-3.0	89 out of 100
#4	supervisionPython toolkit for loading, annotating and counting computer vision detections Live demo ↗ (opens in a new tab)51.2k starsMIT	85 out of 100
#5	pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts37.2k starsApache-2.0	83 out of 100

How to choose

Pick the framework your target models and papers already use.
Check hardware support (CUDA, ROCm, Apple Silicon, TPU) for your machines.
Look at release cadence; a framework that stalls strands your code.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

Apache-2.0 Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#19 of 26 in ML frameworks and libraries on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/huggingface/lerobot.svg)](https://archestack.com/best-of-ai/projects/lerobot/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/lerobot/" title="lerobot on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with lerobot filled in.