Gemini CLI

A command-line AI workflow tool that connects to your tools, understands your code and accelerates your workflows.

Gemini CLI is Google’s open-source AI agent for the terminal, powered by the Google Gemini 2.5 Pro model. It enables natural language interactions directly in the command line, allowing developers to generate, explain, debug, and refactor code, execute shell commands, and perform content or research tasks without leaving their terminal.

The tool offers real-time grounding via Google Search, supports scripting and automation, and is fully extensible through the Model Context Protocol (MCP) and custom prompt files. It’s free to use with generous limits via a Google account and integrates with Gemini Code Assist for consistent workflows across terminal and IDE environments.

With the Gemini CLI you can:

• Query and edit large codebases in and beyond Gemini's 1M token context window.
• Generate new apps from PDFs or sketches, using Gemini's multimodal capabilities.
• Automate operational tasks, like querying pull requests or handling complex rebases.
• Use tools and MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria
• Ground your queries with the Google Search tool, built in to Gemini.