Join us for the first ever LeRobot Live! 🤖 It's our first community event where you will get a chance to talk with our engineers, hear about new features and ask questions. 8th of October at 16:00 CET on LeRobot Discord. discord.gg/UAU6hwXk?event=15…

Humanoids are coming to LeRobot! 🤖 Learn what you can do with the @UnitreeRobotics G1 in LeRobot, how to use @NVIDIARobotics SONIC, and which open-source humanoid hardware we currently support! Read more in our latest blog: huggingface.co/blog/nepyope/…

Introducing Gen-HumanEgo, a more training-ready open-source egocentric human data for robot learning. Powered by our Data Foundation Model (DFM), synchronized Ego video is transformed into training-ready signals: video, action, robust hand tracking, depth, semantic annotations are precisely aligned and encoded into unified tokens — creating a shared representation. We are here to turn real-world human experience into training-ready data, designed to help models learn better. Gen-HumanEgo is a start. #EgoData #Opensource #EmbodiedAI

Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.⁠⁠ FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with @nvidia, we also integrated FLUX 3 Action natively into @huggingface's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).

Kudos to @eidon_ai for open sourcing their hardware! We decided to support their finger tracker in LeRobot! github.com/huggingface/lerob… See it in action: huggingface.co/spaces/lerobo… And build your own! Find BOM (<30$), URDF & assembly guide here: github.com/nepyope/Project-H…

🎉 1,000 datasets have now been recorded with LeLab! Our goal: make the journey from connecting a robot → recording demonstrations → training → real-world testing as accessible as possible 🤗 Thank you to everyone building and experimenting with us ❤️ What we’ve learned + what’s next for LeLab 👇 huggingface.co/spaces/lerobo…

9TB of egocentric video open sourced on @huggingface @eidon_ai is winding down and decided to open-sourced their data. 1,274 hours of first-person housework video, paired with 7-point IMU arm tracking. 13,451 recordings from 27 homes. CC-BY-4.0. huggingface.co/datasets/eido…

1,274 hours of egocentric video with paired 7-IMU arm tracking, now CC-BY-4.0 on @huggingface. @eidon_ai, a robotics company, is winding down and has released all their data: people doing laundry, cleaning, dishes and cooking. 13,451 recordings, 9 TB. huggingface.co/eidon-ai

Egocentric data is more usable when it’s enriched - and available in formats the community can train on. GroundedAPI from @GroundedSI turns raw RoboCap video + IMU into millimeter-fidelity 3D motion data, exportable in LeRobot format (Parquet + MP4) and Hub-ready. Excited to see more large-scale, real-world ego datasets land on the Hub with this release📷

Inspired by MicroDuck? You don’t need a MicroDuck to start building #PhysicalAI. From @huggingface to SO-ARM101, reBot Arm and LeKiwi, open-source robots are making it easier to explore: Data → Learning → Simulation → Policy → Edge AI → Real-world Action Try different paths: • MicroDuck + #Jetson + #MuJoCo + #PPO → #ReinforcementLearning • SO-ARM101 + Hugging Face @LeRobotHF → imitation learning • reBot Arm → perception + manipulation • LeKiwi → mobile manipulation • @NVIDIARobotics Isaac → #Sim2Real Start with one robot. Build one workflow. Then go further. Read full article:👉 seeedstudio.com/blog/2026/09…

Lance is now natively supported in 🤗 @huggingface LeRobot. Ingest through train directly from S3, GCS, or HF Storage Buckets with the same LeRobotDataset API and true global shuffle. No need to download the full robotics dataset first. Big thanks to @Caro_Nahkriin and @lhoestq for working with us to get this merged! na2.hubs.ly/H07PyKN0

Cool robot and tricks! Now try adding even more magic with @LeRobotHF

built the 🤗 @huggingface @LeRobotHF SO-101 arm on a mobile vehicle, running pi0.5 VLA policy. with 1 picking-and-dropping task success rate is 96%🎉, but it doesn’t seem to listen to me yet.