Gemini CLI brings Gemini directly into developers terminals

Free and open source, Gemini CLI brings Gemini directly into developers’ terminals with unmatched access for individuals. For developers, the command line interface (CLI) is not just a tool; it is home. The terminal’s efficiency, ubiquity, and portability make it the go-to utility for getting work done. As developers' reliance on the terminal endures, so does the demand for integrated AI assistance.

Gemini CLI brings Gemini directly into developers terminals: Your open-source AI agent

Google introduced Gemini CLI, an open-source AI agent that brings the power of Gemini directly into the terminal. It provides lightweight access to Gemini, offering a direct path from prompt to model. While it excels at coding, Gemini CLI was built to do much more. It is a versatile, local utility that can be used for a wide range of tasks, from content generation and problem solving to deep research and task management.

Gemini CLI is also integrated with Google’s AI coding assistant, Gemini Code Assist, so that all developers on free, Standard, and Enterprise Code Assist plans get prompt-driven, AI-first coding in both VS Code and Gemini CLI.

Unmatched Usage Limits for Individual Developers

Developers, builders, and creators can bring the power of Gemini 2.5 Pro directly into their terminals with Gemini CLI.

To use Gemini CLI free of charge, users simply log in with a personal Google account to get a free Gemini Code Assist license. That free license provides access to Gemini 2.5 Pro and its massive 1 million token context window. To ensure users rarely, if ever, hit a limit during this preview, Google offers the industry’s largest allowance: 60 model requests per minute and 1,000 requests per day at no charge.

For professional developers who need to run multiple agents simultaneously, or who prefer to use specific models, there is the option to use a Google AI Studio or Vertex AI key for usage-based billing, or to get a Gemini Code Assist Standard or Enterprise license.

Powerful Models in the Command Line

Now in preview, Gemini CLI provides powerful AI capabilities, from code understanding and file manipulation to command execution and dynamic troubleshooting. It offers a fundamental upgrade to the command line experience, enabling users to write code, debug issues, and streamline workflows with natural language.

Its power comes from built-in tools that allow users to:

• Ground prompts with Google Search to fetch web pages and provide real-time, external context to the model
• Extend Gemini CLI’s capabilities through built-in support for the Model Context Protocol (MCP) or bundled extensions
• Customize prompts and instructions to tailor Gemini for specific needs and workflows
• Automate tasks and integrate with existing workflows by invoking Gemini CLI non-interactively within scripts
   

Gemini CLI can be used for a wide variety of tasks, including making a short video showing the story of a ginger cat’s adventures around Australia with Veo and Imagen.

Open and Extensible

Because Gemini CLI is fully open source (Apache 2.0), developers can inspect the code to understand how it works and verify its security implications. Google expects, and welcomes, a global community of developers to contribute to the project by reporting bugs, suggesting features, continuously improving security practices, and submitting code improvements. Issues and ideas can be submitted in the project's GitHub repository.

Gemini CLI was also built to be extensible, building on emerging standards like MCP, system prompts (via GEMINI.md), and settings for both personal and team configuration. The terminal is recognized as a personal space, and everyone deserves the autonomy to make theirs unique.

Shared Technology with Gemini Code Assist

Sometimes, an IDE is the right tool for the job. When that time comes, developers want all the capabilities of a powerful AI agent by their side to iterate, learn, and overcome issues quickly.

Gemini Code Assist, Google’s AI coding assistant for students, hobbyists, and professional developers, now shares the same technology with Gemini CLI. In VS Code, any prompt can be placed into the chat window using agent mode, and Code Assist will work on the developer's behalf to write tests, fix errors, build out features, or even migrate code. Based on the prompt, Code Assist’s agent will build a multi-step plan, auto-recover from failed implementation paths, and recommend solutions that users may not have even imagined.

Gemini Code Assist’s chat agent is a multi-step, collaborative, reasoning agent that expands the capabilities of simple command-response interactions.

Gemini Code Assist agent mode is available at no additional cost for all plans (free, Standard, and Enterprise) through the Insiders channel. Developers not already using Gemini Code Assist can try it. Its free tier has the highest usage limit in the market today, and takes less than a minute to get started. To upgrade the terminal experience with Gemini CLI, users can get started by installing Gemini CLI. All that is needed is an email address to get Gemini practically unlimited in the terminal.

Powerful models in your command line