Trendora
vien

LeRobot

Assess

Tools

A robotics stack for recording datasets, training, and running policies across simulation and hardware.

Why it's here

Placed in Assess: 4 article(s) of evidence from 1 source(s), led by open-source activity, with 1 in the last 30 days. Confidence 45%.

Evidence (4)

  • 7Hugging Face Blog·7/21/2026open_source
    Grabette: Open handheld system for robot manipulation data

    Grabette is an open, low-cost handheld gripper system for recording human manipulation demonstrations and converting them into robot-ready datasets. It is designed to make data collection easier and to support a shared, open dataset for robot learning through the Hugging Face ecosystem and LeRobot.

  • 7Hugging Face Blog·7/7/2026framework_update
    LeRobot v0.6.0 adds world models, reward models, and rollout tooling

    Hugging Face released LeRobot v0.6.0, focusing on closing the robot learning loop with new world model policies, reward model APIs, and a deployment CLI for collecting human corrections into training data. The update also adds new simulation benchmarks, depth sensing, dataset annotation, faster data loading, FSDP training, and cloud training on HF Jobs.

  • 6Hugging Face Blog·6/17/2026open_source
    Hugging Face Hub connects to robots via Strands Agents and LeRobot

    AWS’s Strands Robots SDK integrates LeRobot as AgentTools, letting a single agent handle simulation, dataset recording, policy inference, and deployment to physical robots. The workflow keeps LeRobot datasets in the same on-disk format across simulation and hardware, and can also coordinate multiple robots over a peer mesh.

  • 8Hugging Face Blog·3/9/2026framework_update
    LeRobot v0.5.0 expands robotics support across hardware, policies, and datasets

    LeRobot v0.5.0 is a major release with support for the Unitree G1 humanoid, OpenArm hardware, new CAN bus motor controllers, and additional robot integrations. It also adds new policies such as Pi0-FAST and Real-Time Chunking, faster streaming video dataset encoding, EnvHub for loading simulation environments from Hugging Face Hub, and a modernized codebase built on Python 3.12 and Transformers v5.