Google has recently launched Gemini CLI, an open-source AI agent designed to integrate the power of its Gemini models directly into developers' terminals. Currently in preview, Gemini CLI provides developers with a lightweight yet powerful command-line interface (CLI) for coding assistance, content generation, research, and task automation, marking a significant step in bringing AI closer to the developer workflow.

For many developers, the terminal is a central workspace. With Gemini CLI, Google aims to enhance that space by offering natural language interactions for tasks like code generation, debugging, command execution, and dynamic troubleshooting. While optimized for coding, the tool is built to handle a wide variety of use cases, including content creation and research. Gemini CLI integrates directly with Gemini Code Assist, Google's AI coding assistant, providing prompt-driven AI support in both Visual Studio Code and the terminal. This integration allows developers to seamlessly switch between interfaces without compromising capabilities. Gemini Code Assist and Gemini CLI now share core technology, providing a consistent experience whether developers work in the terminal or inside VS Code.

Gemini CLI is fully open source under the Apache 2.0 license, allowing developers to inspect the codebase, audit security, and contribute via GitHub. The platform supports extensions, prompt customization, and is built on emerging standards like the Model Context Protocol. It also includes support for system prompts using GEMINI.md for personal and team-based workflows. Google encourages developers to help shape Gemini CLI's future by submitting bug reports, suggesting features, or contributing code on GitHub. The tool supports modern standards like the Model Context Protocol (MCP), along with both system-wide and team-based configuration files such as GEMINI.md. Prompts can be tailored, and the model can pull in current web content through integrated Google Search.

Individuals can access Gemini CLI at no cost by logging in with a personal Google account. This grants access to Gemini 2.5 Pro and its 1 million-token context window. The free tier includes 60 model requests per minute and 1,000 per day. For developers with higher usage needs or specific model preferences, usage-based billing is available through Google AI Studio or Vertex AI. Alternatively, users can upgrade to a Standard or Enterprise Code Assist license.

Gemini CLI offers powerful AI capabilities, from code understanding and file manipulation to command execution and dynamic troubleshooting. The AI agent offers an upgrade to one's command line experience, allowing them to write code, debug issues, and streamline their workflow with natural language. Its power comes from built-in tools allowing you to ground prompts with Google Search so you can fetch web pages and provide real-time, external context to the model and extend Gemini CLI's capabilities through built-in support for the Model Context Protocol (MCP) or bundled extensions.

Google has also integrated Gemini CLI 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. In VS Code, you can place any prompt into the chat window using agent mode, and Code Assist will relentlessly work on your behalf to write tests, fix errors, build out features or even migrate your code.