The AI Agent That Works in Your Shell

Gemini CLI marks the third major release in a wave of AI-powered terminal agents. It started with Claude Code in February, followed by OpenAI’s CLI-based Codex in April. Now, in June, Google has entered the arena with Gemini CLI. With this, all three leading AI labs i.e. Anthropic, OpenAI, and Google have introduced their own take on what’s emerging as the next big thing: a “terminal agent”—a command-line tool that can intelligently read, write, and execute files or shell commands on your behalf.

We’re introducing Gemini CLI, an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model. While it excels at coding, we built Gemini CLI to do so much more. — Gemini CLI launch blog

Let’s explore!

Gemini CLI start up screen.

What is Gemini CLI?

Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from prompt to model. While it excels at coding, Gemini CLI can do much more. It’s a versatile, local utility you can use for a wide range of tasks, from content generation and problem solving to deep research and task management.

Gemini CLI is available for developers to preview starting today, and it’s currently free to use through a free Gemini Code Assist license that can be obtained via a personal Google account.

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 by using Gemini’s multimodal capabilities.
• Automate operational tasks, such as 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.

How To Get Started?

npm install -g @google/gemini-cli

• You now have Gemini CLI installed, run it using the gemini command:

gemini

Or install it with:

npm install -g @google/gemini-cli

gemini

• Pick a color theme
• When prompted, sign in with your personal Google account.

You are now ready to use the Gemini CLI!

For Advanced Use or Increased Capacity

If you need to use a specific model or require a higher request capacity, you can use an API key:

1. Generate a key from Google AI Studio.
2. Set it as an environment variable in your terminal. Replace YOUR_API_KEY with your generated key.

export GEMINI_API_KEY="YOUR_API_KEY"

For other authentication methods, including Google Workspace accounts, see the authentication guide.

Unmatched Free-Tier Limits Tailored for Individual Use

To use Gemini CLI free-of-charge, you can simply login with a personal Google account and get a free Gemini Code Assist license. Gemini CLI utilizes Google’s Gemini 2.5 Pro reasoning model, which currently supports a 1 million token context window (the amount of information that an AI model can understand). To ensure you rarely, if ever, hit a limit during this preview, Gemini CLI offers the industry’s largest allowance: 60 model requests per minute and 1,000 requests per day at no charge.

Bring AI Power to Your Terminal

Now in preview, Gemini CLI puts advanced AI directly in your command line. It can understand your code, edit files, run commands, and help you troubleshoot problems, all through simple natural language prompts. Whether you’re writing new code or debugging a tricky issue, Gemini CLI transforms the way you work in the terminal, making your workflow faster, smarter, and more efficient.

What makes Gemini CLI truly powerful is the set of tools it comes with. These tools let you:

• Use Google Search to enhance your prompts, giving the AI access to real-time web content for better, more informed responses
• Expand its capabilities using the Model Context Protocol (MCP) or through built-in extensions
• Customize how it responds by adjusting prompts and instructions to match your unique tasks or workflows
• Automate repetitive work by calling Gemini CLI directly from your scripts—no manual input needed

Final Thoughts

Gemini CLI isn’t just another AI tool BUT it’s a serious upgrade to how developers work. With deep code understanding, smart command execution, real-time web access, and generous free usage limits, it brings the full power of Google’s Gemini model right into your terminal.

Whether you’re debugging, automating, or building something from scratch, Gemini CLI helps you move faster, stay focused, and get more done… with less friction.