Install the Hamster CLI and authenticate with a single command.
Run this in your terminal:
curl -s https://tryhamster.com/cli/install | bash
The script installs the CLI and opens your browser to sign in. After you approve, the session is transferred back to your terminal and you're ready to go. Credentials are stored securely on your machine — you only need to sign in once.
Inside your repository, run:
hamster init
This creates the .hamster/ directory, runs your first sync, and generates the agent skill file. From here, run hamster sync --watch to keep everything up to date as your team works.
If you belong to multiple Hamster teams, switch between them without re-authenticating:
hamster team
The CLI lists your available teams and lets you select which one to work in.
For CI/CD pipelines, containers, or sandboxed environments where a browser isn't available, you can authenticate with environment variables instead:
HAMSTER_ACCESS_TOKEN — Provide a valid access token directlyHAMSTER_REFRESH_TOKEN — Provide a refresh token; the CLI exchanges it for an access token automaticallyWhen environment variables are set, the CLI skips the browser flow entirely.
For SSH sessions or environments without a browser, hamster auth login supports a one-time code flow. The CLI prints a URL and a code — open the URL on any device, enter the code, and the session is issued to your terminal.
The CLI checks for updates automatically and shows a progress indicator when downloading a new version. Updates are verified before installing.
hamster auth login to re-authenticate or switch accounts at any time.hamster sync --watch runs indefinitely without auth interruptions.HAMSTER_ACCESS_TOKEN in your CI/CD environment to use the CLI in automated pipelines without interactive sign-in.