Skip to main content

​
Installation methods

The Timbal CLI provides a command-line interface for managing Timbal projects, including initialization, building, deploying, and other project management tasks.
Use curl to download and execute the installation script:
If your system doesn’t have curl, you can use wget:
The installation script may be inspected before use:
Alternatively, the installer or binaries can be downloaded directly from GitHub.

​
Upgrading

To upgrade the CLI to the latest version, you can either run:
Or re-run the installation script:

​
Uninstallation

To remove the CLI, delete the binary and the ~/.timbal data directory:

​
Python Package

If you want to use Timbal directly in your Python projects or integrate it into an existing codebase, you can install the Python package directly.
Install Python 3.11 or newer before the package. A full timbal create project also needs uv (workforce installs and the server) and Bun (the API and UI). timbal start exits if either is missing.
Using pip:
Or with uv:
Alternatively, if you want the latest changes and want to experiment with beta features, you can clone the repository and install from source:

​
Optional dependencies

Install the extras used by your application:
  • timbal[server]: HTTP server and WebSocket endpoints.
  • timbal[voice]: WebRTC, audio resampling, and local voice turn detection. Combine with server for the voice playground.
  • timbal[voice-livekit]: LiveKit media transport; combine with server,voice for live calls with local detection.
  • timbal[documents]: PDF, Word, and Excel parsing.
  • timbal[evals]: Rich CLI output for evaluations.
  • timbal[codegen]: Code generation and formatting tools.
  • timbal[all]: All of the above.
CSV and plain text do not require document parser extras. External integration examples may need their own SDKs in addition to Timbal.
Next Steps: You’re ready to create your first Timbal project! Continue to the quickstart guide to build your first AI agent.