Almond Axol SDK

Command-line interface and Python SDK for the Almond Axol dual-arm robot. CLI invoked as axol <command> [flags].

The browser front-ends live under web/: a VR teleoperation interface (WebXR, hosted at axol.almond.bot) and a web control panel that drives the robot from a browser via axol serve. See web/README.md for the front-end details.

The full documentation is hosted at docs.almond.bot. The sources live under docs/, and the pages below link to them.

New here? See the Teleoperation quickstart to go from installation to a live teleoperation session, or the Web Control Panel guide to drive Axol from a browser.

Requirements

• Linux
• Python 3.13+
• (Optional) NVIDIA Jetson — if ZED cameras are used.

Installation

Quick install (recommended)

One command installs uv, the axol CLI (from GitHub, with every extra except cuda/dev), and a root systemd service that keeps axol serve running at boot:

curl https://axol.almond.bot/install -fsS | bash

Then open axol.almond.bot and connect to the machine. The install keeps itself in sync with main: when the control panel connects, the server upgrades in the background and restarts onto the new version once idle.

Development install

Install the package from a clone using uv. pyroki and lerobot are sourced from Git and are resolved automatically:

uv sync

Then activate the virtual environment so the axol CLI is on your path (or prefix every command with uv run):

source .venv/bin/activate

Install optional dependency groups as needed:

Extra	Contents	When to use
lerobot	LeRobot (from GitHub)	collect-data, run-policy
sim	viser	teleop --sim
video	aiortc	Streaming the ZED camera feeds to the headset over WebRTC (teleop --zed_host, collect-data)
cuda	JAX with CUDA 13 support	GPU-accelerated JAX (IK solver used by teleop); note that CPU is usually faster for the JAX IK solver
dev	OpenCV (headless)	Development / debugging

uv sync --extra lerobot --extra sim --extra video   # teleoperation + data collection
uv sync --extra lerobot --extra cuda                # policy execution on GPU
uv sync --extra lerobot --extra sim --extra video --extra cuda   # everything

The ZED Python bindings (pyzed) are not on PyPI and must be installed separately after the ZED SDK is installed:

axol zed.install

Before using any motor or robot commands, initialize the CAN hardware:

axol can.setup

To drive Axol from a browser instead of the terminal, build the web UI once (it's served by axol serve):

cd web
npm install
npm run build --workspace=packages/axol-vr-client   # client package first
npm run build --workspace=app                        # → web/app/dist

See the installation guide for the full walkthrough.

Sitemap

Get Started

• Overview
• Installation

Quickstart

• Teleoperation
• Data Collection — two-machine workflow (main host + ZED box)
• Policy Inference — two-machine workflow (main host + ZED box)

Web Interfaces

• Web Control Panel — drive the robot from a browser via axol serve
• VR Interface — the in-repo WebXR teleop app (web/)

CLI Reference

• Command configuration — draccus config model for teleop, gravity-comp, collect-data, run-policy
• serve — web control panel + API server
• can.setup
• can.enable
• can.driver
• motor.info
• motor.set-can-id
• motor.set-zero-pos
• teleop
• collect-data
• run-policy
• zed.stream
• zed.install
• zed.sync-clocks
• tune.pid
• tune.friction
• tune.repeatability
• gravity-comp

Python API

• Core Concepts
• almond_axol.robot — Axol, Sim, configuration, gravity compensation
• almond_axol.kinematics
• almond_axol.teleop
• almond_axol.vr
• almond_axol.zed
• almond_axol.motor
• almond_axol.lerobot