gemini-cli/docs/cli/index.md

Using Gemini CLI

Gemini CLI is a terminal-first interface that brings the power of Gemini AI models directly into your development workflow. It lets you interact with AI using your local files, shell environment, and project context, creating a bridge between generative AI and your system tools.

User guides

These guides provide step-by-step instructions and practical examples for using Gemini CLI in your daily development workflow.

• Quickstart: Get up and running with Gemini CLI in minutes.
• Examples: See practical examples of Gemini CLI in action.
• Get started with skills: Learn how to use and manage specialized expertise.
• File management: How to include, search, and modify local files.
• Set up an MCP server: Configure Model Context Protocol servers for custom tools.
• Manage context and memory: Manage persistent instructions and individual facts.
• Manage sessions and history: Resume, manage, and rewind your conversations.
• Execute shell commands: Execute system commands safely directly from your prompt.
• Plan tasks with todos: Using todos for complex, multi-step agent requests.
• Web search and fetch: Searching and fetching content from the web.

Features

Technical reference documentation for each capability of Gemini CLI.

• /about: Show version info.
• /auth: Change authentication method.
• /bug: File an issue about Gemini CLI.
• /chat: Save and resume conversation history.
• /clear: Clear the terminal screen.
• /compress: Replace context with a summary.
• /copy: Copy output to clipboard.
• /directory: Manage workspace directories.
• /docs: Open documentation in browser.
• /editor: Select preferred editor.
• /extensions: List active extensions.
• /help: Display help information.
• /hooks: Manage hooks for lifecycle events.
• /ide: Manage IDE integration.
• /init: Create a GEMINI.md context file.
• /mcp: Manage Model Context Protocol servers.
• /memory: Manage instructional context.
• /model: Choose Gemini model.
• /policies: Manage security policies.
• /privacy: Display privacy notice.
• /quit: Exit Gemini CLI.
• /restore: Restore file state.
• /resume: Browse and resume sessions.
• /rewind: Navigate backward through history.
• /settings: Open settings editor.
• /setup-github: Set up GitHub Actions.
• /shells: Toggle background shells view.
• /skills: Manage Agent Skills.
• /stats: Display session statistics.
• /terminal-setup: Configure keybindings.
• /theme: Change visual theme.
• /tools: Display list of available tools.
• /vim: Toggle vim mode.
• Activate skill (tool): Internal mechanism for loading expert procedures.
• Ask user (tool): Internal dialog system for clarification.
• Checkpointing: Automatic session snapshots.
• File system (tool): Technical details for local file operations.
• Headless mode: Programmatic and scripting interface.
• Internal documentation (tool): Technical lookup for CLI features.
• Memory (tool): Storage details for persistent facts.
• Model routing: Automatic fallback resilience.
• Plan mode (experimental): Use a safe, read-only mode for planning complex changes.
• Sandboxing: Isolate tool execution.
• Shell (tool): Detailed system execution parameters.
• Telemetry: Usage and performance metric details.
• Todo (tool): Progress tracking specification.
• Token caching: Performance optimization.
• Web fetch (tool): URL retrieval and extraction details.
• Web search (tool): Google Search integration technicals.

Configuration

Settings and customization options for Gemini CLI.

• Custom commands: Personalized shortcuts.
• Enterprise configuration: Professional environment controls.
• Ignore files (.geminiignore): Exclusion pattern reference.
• Model configuration: Fine-tune generation parameters like temperature and thinking budget.
• Project context (GEMINI.md): Technical hierarchy of context files.
• Settings: Full settings.json schema.
• System prompt override: Instruction replacement logic.
• Themes: UI personalization technical guide.
• Trusted folders: Security permission logic.

Next steps

• Explore the Command reference to learn about all available slash commands.
• Read about Project context to understand how to provide persistent instructions to the model.
• See the CLI reference for a quick cheatsheet of flags.