Google Launches Gemini CLI: Open-Source AI Agent for the Developer Terminal

Google has released Gemini CLI, an open-source AI agent designed to bring the power of its Gemini models directly into developers’ terminals. Now in preview, Gemini CLI offers developers a lightweight yet powerful command-line interface for coding assistance, content generation, research, and task automation.

Command Line Meets Generative AI

For many developers, the terminal is a central workspace. With Gemini CLI, Google aims to elevate 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. This integration provides prompt-driven AI support in both Visual Studio Code and the terminal, enabling developers to seamlessly switch between interfaces without compromising capabilities.

Generous Free Usage for Individual Developers

Users 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 — among the highest available today. The free tier includes 60 model requests per minute and 1,000 per day, making it one of the most generous allowances currently on the market.

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.

Customizable, Extensible, and Open Source

Gemini CLI is fully open source under the Apache 2.0 license, enabling 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.

According to Google, “We know the terminal is a personal space, and everyone deserves the autonomy to make theirs unique.”

Seamless Experience Across Terminal and IDE

Gemini Code Assist and Gemini CLI now share core technology, providing a consistent experience whether developers work in the terminal or inside VS Code. In IDE chat mode, Code Assist creates multi-step plans, recovers from failed implementations, and suggests novel solutions, making it a versatile AI pair programmer.

Getting Started

Developers can begin using Gemini CLI by installing it and logging in with an email address. No payment is required to access the robust free tier, making it an easy entry point for professionals, hobbyists, and students alike.

Gemini CLI marks a significant move in democratizing access to high-performance AI tools within the workflows developers use most.