LeRobot

LeRobot v0.6.0 is officially here: Imagine, Evaluate, Improve! 🤖🚀 We are closing the robot learning loop with massive upgrades for the open-source robotics community. From policies that imagine the future to a much leaner installation, here is what is new: - 🌍 World Models: VLA-JEPA, LingBot-VA, and FastWAM help your policies anticipate the future. - 👀 VLA Expansion: Welcome GR00T 1.7, MolmoAct2, EO-1, Multitask DiT, and EVO1. - 🏅 Reward Models API: Track success seamlessly with Robometer and TOPReward. - 🎯 Unified Evaluation: 6 new simulation benchmarks, all accessible via the lerobot-eval CLI. - ☁️ And more: lerobot-rollout CLI for DAgger corrections, HF Jobs cloud training, up to 2x faster data loading, GUI - LeLab, many docs improvements Ready to build the future of robotics? Dive into the full release notes here: huggingface.co/blog/lerobot-r… @ClementDelangue @Thom_Wolf

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 @allen_ai open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

GR00T 1.7 just landed in LeRobot 🟢 We upgraded our @NVIDIARobotics GR00T integration to 1.7, the newest open generation of NVIDIA's cross-embodiment foundation model. It swaps the previous VLM for Cosmos-Reason2-2B feeding a flow-matching action head, and we parity-tested it against NVIDIA's own Isaac GR00T implementation: same inputs, same outputs. Flash-attention is now optional too, so pip install 'lerobot[groot]' just works, and you can load NVIDIA's published checkpoints directly. Isaac Teleop is now in the ecosystem too, letting you drive an SO-101 with a VR controller over CloudXR/OpenXR.

@ByFrustrated Take a look at SO-ARM101, it's open source so you can print the parts on your own and the other parts that you need. You can also buy a kit with everything included. More info here: github.com/TheRobotStudio…

@LeRobotHF What robot kits is everyone using that’s cheap?

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

Full details on LeRobot 0.6.0: huggingface.co/blog/lerobot-r…

LingBot-VLA 2.0 is bringing causal world modeling to open-source robotics. By natively unifying visual dynamics prediction and action inference, this new foundation model handles complex, long-horizon tasks with incredible efficiency. It was trained on 60,000 hours of diverse data to achieve true whole-body control - managing everything from dexterous hands to mobile bases seamlessly across 17 different hardware brands. Despite the heavy lifting, its dual-stream Mixture-of-Transformers architecture keeps inference ultra-fast, under 130ms on a standard RTX 4090. Explore the pre-trained checkpoints in the Hugging Face collection: huggingface.co/collections/ro…

It depends on the policies. The one shown at the beginning of the video is MolmoAct2 running zero shot on SO-ARM101, it was't trained on this specific setup!

@LeRobotHF Sorry for the noob question but why is LeRobot always jittering like this in most videos? Is this a motor problem? Can it not be smoothed out?

LeRobot v0.6.0 is officially here: Imagine, Evaluate, Improve! 🤖🚀 We are closing the robot learning loop with massive upgrades for the open-source robotics community. From policies that imagine the future to a much leaner installation, here is what is new: - 🌍 World Models: VLA-JEPA, LingBot-VA, and FastWAM help your policies anticipate the future. - 👀 VLA Expansion: Welcome GR00T 1.7, MolmoAct2, EO-1, Multitask DiT, and EVO1. - 🏅 Reward Models API: Track success seamlessly with Robometer and TOPReward. - 🎯 Unified Evaluation: 6 new simulation benchmarks, all accessible via the lerobot-eval CLI. - ☁️ And more: lerobot-rollout CLI for DAgger corrections, HF Jobs cloud training, up to 2x faster data loading, GUI - LeLab, many docs improvements Ready to build the future of robotics? Dive into the full release notes here: huggingface.co/blog/lerobot-r… @ClementDelangue @Thom_Wolf

@IsaacSin12 @pham_blnh This has been fixed already! Update LeRobot and follow this: #hardware-deployment-lerobot-rollout" target="_blank" rel="nofollow noopener">huggingface.co/docs/lerobot/m…

Tried to get MolmoAct2 to zero-shot pick up a cube with an SO101. The shoulder lift servo just slammed straight into the table. Finally got it working with @pham_blnh's help. The checkpoint is trained in old SO-100-era degrees (pre-PR #777). Newer SO-101 calibration flips + offsets the shoulder/elbow zero and normalizes units. If you try using the new calibration on the policy zero shot, arm slams down instead of lifting. Fixes are in this @LeRobotHF fork: github.com/makermods-robo…

This weekend, our team won Paris Builds, a 36-hour selective hackathon by @Unaite, in partnership with @ycombinator. In just 36 hours, we built VIGIE, a robot safety watchdog & harness, an external runtime safety layer for learning-based robots. It watches the robot and its workspace through cameras from the environment, detects dangerous situations, and can pause, hold, and resume a real OpenARM / LeRobot run when the scene becomes unsafe — with a demo harness interfaced with the @LeRobotHF framework. The core idea behind VIGIE is that robot safety should not depend only on the robot policy itself. Today, most robots still operate with little to no external safety harness. The robot executes actions, but there is no independent runtime layer continuously asking: “Is the current scene still safe?” “Is a human hand entering the workspace?” “Is the robot about to continue an action that became dangerous?” We see this as a layered roadmap. Huge shoutout to Joseph @Batatasfri13181 , Maelic, Tristan @tristanlecourt and Raph, amazing sprint. A very special thank you to Alba @leader_arm for helping us set up the OpenARM. Huge thanks as well to @Unaite for organizing the event, and to the mentors, jury members, and partners who pushed us throughout the weekend — including @dessaigne, people from @gs_ai_ , @MistralAI , Qube Research & Technologies, and the broader ecosystem around the event. Big thanks to Stephenson Harwood Paris for hosting us in central Paris. And the cherry on top: winning the hackathon means we earned a YC interview for a chance to join a future batch, which is an incredible opportunity. Repo here: github.com/TristanLecourt…

I placed 🥈 2nd in the LeHome Challenge (at @ieee_ras_icra 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

You don't need hardware to play with robots! Thanks to this project you can have SO-ARM101 running an ACT policy inside your browser. Really cool project!

The largest open-source humanoid teleop dataset EVER just dropped on @LeRobotHF @huggingface huggingface.co/datasets/BitRo… We re-encoded the full dataset into LeRobot format: ~10TB → ~2TB, no loss of fidelity. Same trajectories, a fraction of the footprint, far easier to stream and train on. Explore the dataset in LeRobot Visualizer: live 3D render of the robot, synced camera feeds, subtask annotations and language instructions, all in your browser. Most importantly: Unitree G1 is supported in LeRobot, meaning you can load HIW-500 and start training imitation / VLA policies on 20,000 real-home humanoid episodes on your G1. Huge thanks to @BitRobotNetwork for sharing the data. Go build. 🤖

Have you thought where all that physical AI data should live? 🤖 If you haven’t, 𝗶𝘁’𝘀 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝗰𝗼𝘀𝘁𝗶𝗻𝗴 𝘆𝗼𝘂 𝗮 𝗹𝗼𝘁. Unoptimized storage, egress fees, and idle GPUs will drain your budget. Check out why & how to reduce your bill: huggingface.co/spaces/imsteve…

Is it really worth it joining a robotics hackathon? One year ago, thousands of people around the world spent a single weekend building AI robots using the open-source LeRobot stack. Many had never built a robot before. We sat down with the winners to ask what they made and where they are now. For many of them, that weekend changed everything, turning the intimidating field of AI robotics into an accessible hobby or even a full-time career. Here are a few key takeaways from their year-long journey: - You don't need a PhD to start. For many participants, this was their very first robot - One weekend can launch a career. Winning secured internships and full-time jobs - Community lowers the barrier to entry - Learning by doing is exponentially faster. Robotics still requires getting your hands dirty to truly progress Watch the full video to see their projects and hear their advice for taking the first step. @ClementDelangue, @Thom_Wolf

@VMises76153 Here is a link to the full video: youtube.com/watch?v=vsL1EH…

Cleaning your home with Cable-Driven Parallel Robot and LeRobot. Meet Stringman, an open-source project by Nathaniel Nifong (@VMises76153). The goal is to completely automate picking up household laundry, toys, and trash. It operates as an overhead Cable-Driven Parallel Robot (CDPR) using 4 wall-mounted motors and fishing line. Offloading the motor weight from the end-effector keeps the moving gripper assembly lightweight, incredibly cheap, and quiet while maximizing payload capacity. Most of the parts are 3D printed. The technical stack: - Model: Multitask Diffusion Transformer (DiT) - Data: Learned via teleoperation and trained on just 400 local human demonstration examples - Framework: Built and trained locally using LeRobot on a consumer GPU This is a fantastic showcase of how accessible, community-driven hardware and open-source AI can rethink home automation constraints without needing a complex humanoid base.

Very cool and massive dataset on @huggingface of course: huggingface.co/datasets/XDOF/…!

🤗 LeLab now keeps itself up to date! 🦾 We shipped an in-app popup that alerts you the moment a newer version is on GitHub - plus same upgrades based on users feedback: - Import any external/Hub model to run & rollout, no retraining - Per-camera codec & backend control when recording - Warning when your GPU is present but CUDA isn't being used - Real camera names on Windows & Linux - Smoother calibration & teleop (cameras stay off until you turn them on 🛠️ Update now with: uv tool install --force git+github.com/huggingface/le… GitHub: github.com/huggingface/le… Docs: huggingface.co/docs/lerobot/m…