Skip to main content
Dropbear supports Python 3.11 through 3.14 for cloud policy inference. The current release is 0.1.0a9. Install only the extras required by your local robot or simulator stack.

​
Choose an install

The base package includes the Python SDK, CLI, transport, and observation helpers.
Dropbear is pre-release, so install the latest version rather than pinning an old one. Each release tracks what the hosted models actually serve; an out-of-date SDK can disagree with the live control rate for a model. Pin an exact version (dropbear==<version>) when you need a reproducible run, and refresh the pin when you upgrade.
Install an extra in the project that owns the corresponding hardware or simulator:
Your own Franka or simulator integration should use its existing controller dependencies plus the base dropbear package. Dropbear does not provide a Franka controller.

​
Sign in

Browser login is the default:
The CLI opens a one-time approval page. After approval, it verifies the credential and writes ~/.dropbear/config.toml with user-only permissions. For a headless machine, paste an API key into the hidden prompt:
You can also pass an API key as the option value, but shell history and process inspection can expose it. Prefer the hidden prompt or an existing secret manager.
Do not commit ~/.dropbear/config.toml, paste keys into source files, or log them in CI. Create and revoke keys in the dashboard.

​
Verify the machine

doctor checks the robot-neutral installation, authentication, and network path. status reports live model-region capacity without opening a session. If either command fails, use the command’s printed recovery step and then open Troubleshooting.

​
Upgrade

Update both the project dependency and standalone CLI so their behavior stays aligned:
You are ready when dropbear --help lists login, doctor, sim, status, run, robots, and sessions. Continue to the Python quickstart to request one non-actuating prediction.