Gemini CLI

Within Gemini CLI, packages/cli is the frontend for users to send and receive prompts with the Gemini AI model and its associated tools. For a general overview of Gemini CLI, see the main documentation page.

Basic features

• Commands: A reference for all built-in slash commands
• Custom commands: Create your own commands and shortcuts for frequently used prompts.
• Headless mode: Use Gemini CLI programmatically for scripting and automation.
• Model selection: Configure the Gemini AI model used by the CLI.
• Settings: Configure various aspects of the CLI's behavior and appearance.
• Themes: Customizing the CLI's appearance with different themes.
• Keyboard shortcuts: A reference for all keyboard shortcuts to improve your workflow.
• Tutorials: Step-by-step guides for common tasks.

Advanced features

• Checkpointing: Automatically save and restore snapshots of your session and files.
• Enterprise configuration: Deploying and manage Gemini CLI in an enterprise environment.
• Sandboxing: Isolate tool execution in a secure, containerized environment.
• Telemetry: Configure observability to monitor usage and performance.
• Token caching: Optimize API costs by caching tokens.
• Trusted folders: A security feature to control which projects can use the full capabilities of the CLI.
• Ignoring files (.geminiignore): Exclude specific files and directories from being accessed by tools.
• Context files (GEMINI.md): Provide persistent, hierarchical context to the model.

Non-interactive mode

Gemini CLI can be run in a non-interactive mode, which is useful for scripting and automation. In this mode, you pipe input to the CLI, it executes the command, and then it exits.

The following example pipes a command to Gemini CLI from your terminal:

echo "What is fine tuning?" | gemini

You can also use the --prompt or -p flag:

gemini -p "What is fine tuning?"

For comprehensive documentation on headless usage, scripting, automation, and advanced examples, see the Headless mode guide.