Skip to main content
The one-command install is the right path for running Axol on the robot machine. This page is for working on Axol itself — installing from a clone, picking optional dependency extras, and building the web UI locally. If you just want to use the robot, you don’t need any of this.

​
Install from a clone

Install the package from a checkout using uv. pyroki and lerobot are sourced from Git and resolved automatically:
Then activate the virtual environment so the axol CLI is on your path:
You need to activate the environment in every new shell session. Alternatively, prefix every command with uv run (e.g. uv run axol can.setup) to skip activation.

​
Optional extras

Install optional dependency groups as needed (the install script includes lerobot and sim):
Streaming the ZED camera feeds to the headset (teleop --cameras, collect-data) isn’t a dependency extra — it needs the system GStreamer + camera stack, installed via axol provision (see Headset-video stack below).

​
ZED Python bindings

The ZED Python bindings (pyzed) are not on PyPI and must be installed separately, after the ZED SDK is installed:
See zed.install for details.

​
Headset-video stack

Relaying the ZED cameras to the headset grabs and NVENC-encodes frames on the GPU via the zed-gstreamer pipeline (zedxonesrc / zedsrc) and sends them over WebRTC with aiortc (a normal Python dependency). The encode path needs the system GStreamer + GObject-introspection packages, PyGObject, and the patched ZED source elements — none of which are PyPI extras. axol provision installs all of them idempotently in one step (the same command the install script and the axol serve self-updater run):
This runs the Quest-over-USB adb setup, zed.install, gst.install, and gst.build-zed in order; each self-gates and no-ops if the ZED SDK or apt isn’t present. You can also run them individually. On a Jetson, pin the NVENC/VIC and CPU clocks for low-latency encode and a steady IK loop (the install script wires this into the systemd unit so it re-runs at every boot):
See jetson.setup. It’s a no-op on non-Jetson machines.

​
First-run hardware setup

Before using any motor or robot commands, initialize the CAN hardware once:
sudo is invoked automatically where required. See can.setup for what it configures, and can.enable for bringing the interfaces back up after a mid-session replug.

​
Build the web UI

axol serve looks for the built web bundle at web/app/dist. To serve the control panel and VR interface from your own machine, build it once:
Then start the server and open the printed URL:
axol serve works without this step (the API is still available) — the hosted UI at axol.almond.bot connects to it directly. See serve and the Web Control Panel guide.

​
Next steps

CLI Reference

Every axol command, flag, and the draccus config model.

Python API

Axol, the kinematics solver, VR teleop, and the LeRobot wrappers.