LeRobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning observed · 2026-10-17
Health v2 · maintenance only
90/100
- Activity 100
- Release rhythm 89
- Longevity 71
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 28.5
- age_days: 998
- days_rel: 78
- days_push: 4
- n_releases_24m: 11
Adoption not part of the score
28232 stars · 5899 forks observed · 2026-10-17
What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.97
LeRobot is a Python library that provides a unified interface for controlling real robots, recording datasets, and training/deploying policies. It includes CLI tools and a GUI (LeLab) for end‑to‑end robotics workflows.
Use cases
- train a robot policy from teleoperated demonstrations
- collect and stream large robot datasets using the LeRobotDataset format
- control a physical robot from Python code across different hardware platforms
- evaluate and deploy pretrained robot policies on edge devices
- run end‑to‑end imitation‑learning pipelines for real‑world robots
When to choose
- You need a hardware‑agnostic, Python‑native API for robot control and data collection.
- You want to leverage community datasets and pretrained policies hosted on Hugging Face.
- You prefer an integrated CLI and optional GUI to manage the full robot‑learning workflow.
When to avoid
- Your application requires ultra‑low‑latency real‑time control beyond Python performance.
- You are working in non‑PyTorch environments or need support for languages other than Python.
- The target robot hardware is not supported and cannot be integrated via the provided base class.
Facets
library · maturity active
api-framework cli gui machine-learning data-science artificial-intelligence robotics data-science python windows hardware-agnostic state-of-the-art-policies standardized-dataset-format teleoperation-support linux macos docker
10 sources
- readme: https://github.com/huggingface/lerobot · fetched 2026-10-17 · 6d8b7fcacd6e
- homepage: https://huggingface.co/docs/lerobot · fetched 2026-09-21 · c7f6a95cb533
- site_page: https://huggingface.co/docs · fetched 2026-09-21 · bdec26667b98
- site_page: https://huggingface.co/docs/lerobot/installation · fetched 2026-09-21 · d04798b53c4f
- site_page: https://huggingface.co/docs/lerobot/cheat-sheet · fetched 2026-09-21 · bbd39396b973
- site_page: https://huggingface.co/docs/lerobot/il_robots · fetched 2026-09-21 · 2b61be0dceb1
- site_page: https://huggingface.co/docs/lerobot/lelab · fetched 2026-09-21 · 184359afc565
- site_page: https://huggingface.co/docs/lerobot/bring_your_own_policies · fetched 2026-09-21 · bdba4e826dae
- site_page: https://huggingface.co/docs/lerobot/integrate_hardware · fetched 2026-09-21 · 572d5a744cc4
- registry_pypi: https://pypi.org/pypi/gym-hil/json · fetched 2026-09-21 · 565709a671fb
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| huggingface/lerobot | main | 90 |
| huggingface/gym-hil | plugin | 63 |
| huggingface/VLAb | sdk | 38 |
| huggingface/leLab | frontend | 59 |
| huggingface/robotics-course | docs | 62 |
| huggingface/lerobot-dataset-visualizer | examples | 62 |
For agents
markdown · JSON · MCP: product_card(name="huggingface/lerobot")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem