Skip to main content
This guide takes you from nothing to a live agent in a handful of commands. Run them in order; each one builds on the last. First, install the Zero Runtime CLI with pip (Python 3.11+), and make sure Docker is running (needed for zrt up):
See CLI Setup for more detail.
Run every zrt command from inside your project folder. The CLI reads and writes a zrt.yaml file there to remember your agent, image, and version, so most commands need no flags at all.
1

Sign in

Authenticate the CLI with your Zero Runtime account. This opens your browser to confirm the login, then stores your token on this machine:
You only need to do this once per machine. To sign out later, run zrt auth logout.
2

Create a project

The fastest way to get a working agent is zrt quickstart. It downloads a ready-made example into a new folder and runs it locally so you can talk to it right away.
You’ll be asked to pick an example, or skip the picker by naming one (replace <example-id> with the example you want):
This creates a ./<example-id>/ folder with everything you need:
Already have an agent project? You can skip this step. Just make sure it has an entrypoint named main.py, agent.py, or app.py. zrt init (below) generates the Dockerfile and zrt.yaml for you.
3

Add your provider keys

Move into the project folder (the one quickstart just created) and open .env. Fill in the API keys for the STT, LLM, and TTS providers your agent uses:
.env
zrt run and your deployed agent both read keys from this .env file. Never commit it or bake keys into the Docker image.
4

Test it locally

Run the agent on your own machine to confirm it works before deploying. This creates a virtual environment, installs the requirements, and starts the agent in the playground so you can talk to it in your browser:
Expected output
Prefer your terminal over the browser? Run in console mode instead:
You can also run a single file directly: zrt run main.py --console.
This runs entirely on your machine; no cloud resources are used yet.
5

Initialize the deployment

Register the agent with Zero Runtime Cloud. This creates the IDs your later commands need, writes them to zrt.yaml, and generates a Dockerfile if your project doesn’t have one:
After it runs, zrt.yaml holds your agent.id and deploy.id:
zrt.yaml
You won’t edit zrt.yaml by hand. Each command fills in the values it produces (image name, version ID, secrets), so the commands that follow run with no flags.
6

Deploy it

zrt up deploys your agent to Zero Runtime Cloud in a single command. Pass --env .env to also upload your provider keys so the deployed agent can use them:
Expected output
That’s it. Your agent is now running on Zero Runtime Cloud. The new version.id is saved to zrt.yaml.
zrt up deploys with sensible defaults, so there’s nothing else to configure.
This step needs Docker running. If you see 'docker' command not found, make sure Docker is installed and running, then try again.
7

Confirm it's live

Check that the version deployed and is healthy:
8

Talk to your agent

Invoke your agent to start it in a room. The CLI prints a playground link you can open to talk to it:
Expected output
Want to talk to it right in your terminal? Add --console:
List and stop live sessions when you’re done:
9

Watch the logs

Stream your agent’s console output to see what it’s doing in production:
See Managing Deployments for time filters.

​
Ship an update

Changed your code? Redeploy with the same command; it creates a new version:

​
Take it down

When you’re finished, stop the running version(s) so they stop using resources:
This lists the active versions and asks you to confirm. Add --yes to skip the prompt, or --force if a version still has active sessions.

​
What’s next

Managing Deployments

Versions, secrets, sessions, and logs for a live agent.

CLI Reference

Every command and flag in one place.