Native Foxglove Visualization in LeRobot

LeRobot 0.6.0 now includes native Foxglove visualization support, enabling live streaming of teleoperation, recording, and dataset playback without custom code. Users can add a single flag to stream camera feeds and joint data over WebSocket, and replay datasets as seekable timelines. This integration simplifies imitation learning workflows by providing real-time feedback and consistent topic layouts across live and replay modes.

Native Foxglove Visualization in LeRobot Stream teleop, recording, and dataset playback from LeRobot straight into Foxglove without any code tl;dr LeRobot https://github.com/huggingface/lerobot 0.6.0 ships native Foxglove support. Add --display mode=foxglove to lerobot-teleoperate , lerobot-record , or lerobot-rollout to stream camera feeds and joint/action plots live over WebSocket. Replay any recorded dataset as a seekable timeline with lerobot-dataset-viz --display-mode foxglove . Connect the Foxglove app to ws://localhost:8765 and you’re done — no custom integration code required. With PR 3902 https://github.com/huggingface/lerobot/pull/3902 , Foxglove becomes a first-class visualization backend for LeRobot — selectable at runtime with a single flag. We are excited about this development and can’t wait to see how the community embraces simpler workflows. Why Foxglove for LeRobot LeRobot’s control loop produces a rich mix of data every timestep: per-motor joint positions, action targets, one or more camera images, and optionally depth maps. Foxglove’s multi-panel layouts let you see all of this side by side — camera feeds in Image panels, joint traces in Plot panels, all synced to the same timeline. Three things make this integration useful for imitation learning workflows: Live feedback during teleop and recording. Spot a dead camera, a stuck joint, or a misaligned gripper before you’ve recorded fifty episodes. The Foxglove app updates in real time as you move the leader arm. Seekable dataset playback. Recorded episodes are served as a scrubbable timeline using Foxglove’scapability. Play, pause, seek, and change speed — frames are read from the on-disk dataset on demand and stamped at their original timestamps. PlaybackControl Consistent topic layout across live and replay. Whether you’re streaming live or replaying a dataset, data appears on the same topics: /observation/state , /action/state , and /observation/images/<camera . Build a layout once and reuse it everywhere. Under the hood, LeRobot uses the Foxglove SDK https://github.com/foxglove/foxglove-sdk foxglove-sdk =0.25.1 to start a WebSocket server. Scalar features are published as typed JSON messages on a static lerobot.Scalars schema — a flat {label, value} array so every joint and action dimension is automatically named in Plot panels. Images are published as RawImage or JPEG CompressedImage when compression is enabled . Getting started LeRobot requires Python 3.12+. We run it using uv, but conda is also supported. uv venv --python 3.12 source .venv/bin/activate uv pip install 'lerobot feetech,dataset viz ' Refer to LeRobot Installation documentation https://huggingface.co/docs/lerobot/v0.6.0/en/installation for more information. Connect Foxglove - In the Foxglove app, select Open connection from the dashboard or left-hand menu. - Choose Foxglove WebSocket and enter ws://localhost:8765 the default bind address . - Start any LeRobot command with --display mode=foxglove live or --display-mode foxglove dataset replay — data appears as soon as the server starts. Download our layout https://github.com/foxglove/foxglove-sdk/blob/main/python/foxglove-sdk-examples/so101-visualization/foxglove/lerobot layout.json for LeRobot or create your own https://docs.foxglove.dev/docs/visualization/layouts . We show you how to open a layout in Foxglove in this video https://youtu.be/TathDUV1ad0 . Live teleoperation The fastest way to see Foxglove in action is during teleoperation. Pass --display data=true --display mode=foxglove to lerobot-teleoperate and move the leader arm — camera feeds and joint plots update in the Foxglove app in real time. uv run lerobot-teleoperate \ --robot.type=so101 follower \ --robot.port=/dev/tty.usbmodemFOLLOWER \ --robot.id=my follower \ --robot.cameras="{ front: {type: opencv, index or path: 0, width: 640, height: 480, fps: 30}}" \ --teleop.type=so101 leader \ --teleop.port=/dev/tty.usbmodemLEADER \ --teleop.id=my leader \ --display data=true \ --display mode=foxglove Replace the USB port paths with your actual device paths find them with lerobot-find-port . Each motor’s position appears as a named series on /observation/state , and the teleoperator’s targets appear on /action/state . Camera frames stream to /observation/images/front . Recording with live visualization When collecting demonstration data, live visualization is invaluable for catching problems early. Add the same flags to lerobot-record , and you’ll see exactly what the dataset will contain as each episode is captured. uv run lerobot-record \ --robot.type=so101 follower \ --robot.port=/dev/tty.usbmodemFOLLOWER \ --robot.id=my follower \ --robot.cameras="{ front: {type: opencv, index or path: 0, width: 640, height: 480, fps: 30}}" \ --teleop.type=so101 leader \ --teleop.port=/dev/tty.usbmodemLEADER \ --teleop.id=my leader \ --dataset.repo id=${HF USER}/foxglove-demo \ --dataset.num episodes=5 \ --dataset.single task="Pick up the cube" \ --display data=true \ --display mode=foxglove The live Foxglove panel gives you instant feedback on camera framing, joint ranges, and action tracking — much easier than discovering a bad episode after recording dozens of them. Seekable dataset playback The most powerful part of this integration is dataset replay. lerobot-dataset-viz can serve any LeRobot dataset — from the Hugging Face Hub or recorded locally — as a seekable timeline in Foxglove. The playback bar drives play, pause, seek, and speed; frames are read from disk on demand and stamped at their original dataset timestamps. A public SO-101 pick-and-place dataset uv run lerobot-dataset-viz \ --repo-id lerobot/svla so101 pickplace \ --episode-index 0 \ --display-mode foxglove A dataset you recorded locally uv run lerobot-dataset-viz \ --repo-id ${HF USER}/foxglove-demo \ --root ~/.cache/huggingface/lerobot/${HF USER}/foxglove-demo \ --episode-index 0 \ --display-mode foxglove This uses the same PlaybackControl capability described in our earlier post on local player integration /blog/connect-foxglove-to-your-local-player-with-playback-control . LeRobot advertises the episode’s time range, and the Foxglove app sends playback commands back to the server. A background thread reads frames from the on-disk dataset for whatever time you scrub to — no need to load the entire episode into memory upfront. Dataset replay also publishes episode metadata done , truncated , reward , success on /episode/state , and uses the dataset’s feature metadata to label each scalar series with the correct joint names. Policy rollout visualization The same flags work for policy evaluation. When running lerobot-rollout , add --display data=true --display mode=foxglove to watch a trained policy execute in Foxglove — useful for comparing what the policy observes and commands against what you demonstrated during recording. Tips and options A few handy flags beyond the basics: | Goal | Live commands teleoperate / record / rollout | Dataset replay lerobot-dataset-viz | |---|---|---| | JPEG-compress images | --display compressed images | --display-compressed-images | | Custom port | --display port=8766 | --web-port 8766 | | Stream to another machine | --display ip=0.0.0.0 | --host 0.0.0.0 | | Don’t auto-play on connect | — | --no-autoplay | When streaming to another machine, connect the Foxglove app to ws://<robot-ip :8765 instead of localhost . Depth images: if your robot has a depth camera, LeRobot handles it automatically. During live streaming, depth values are normalized for display contrast. During dataset replay, raw depth measurements are preserved so you can inspect the actual values. Flag naming: live commands use underscores --display mode , --display data while lerobot-dataset-viz uses hyphens --display-mode . This matches each tool’s CLI convention — just something to watch for when switching between workflows. What’s next LeRobot’s Foxglove integration covers the full imitation learning loop: teleoperate, record, replay, and evaluate — all through the same WebSocket topics and schemas. No need to roll it out yourself anymore. To go further, check out the Foxglove SDK examples https://github.com/foxglove/foxglove-sdk/tree/main/python/foxglove-sdk-examples for building custom visualizations on top of LeRobot’s topic layout — like a live 3D kinematic model driven from joint positions. Resources: LeRobot Foxglove visualization source https://github.com/huggingface/lerobot/blob/main/src/lerobot/utils/foxglove visualization.py LeRobot dataset visualization docs https://huggingface.co/docs/lerobot/en/using dataset tools Foxglove PlaybackControl documentation https://docs.foxglove.dev/docs/sdk/websocket-server playback-control Foxglove WebSocket connections https://docs.foxglove.dev/docs/connecting-to-data/frameworks/custom foxglove-websocket Download the latest Foxglove desktop app /download and try it with your LeRobot setup today. Join our Discord https://foxglove.dev/community community or follow us on X https://x.com/foxglove and LinkedIn https://www.linkedin.com/company/foxglovedev to stay up to date on all Foxglove releases.