Google launches Gemini CLI, an open-source tool that brings Gemini AI directly to the command line.
The new utility is built on the same technology as Gemini Code Assist, Google's AI coding assistant, and is designed for developers who want to integrate AI features as seamlessly and locally as possible into their workflows.
Gemini CLI can handle a wide range of tasks, from understanding code and manipulating files to running commands, debugging, researching, and generating content. It can also be integrated into local scripts to automate repetitive work.
Video: Google
Individuals can use Gemini CLI for free by signing in with a personal Google account. This unlocks Gemini 2.5 Pro with a one-million-token context window through a complimentary Gemini Code Assist license. During the preview phase, Google allows up to 60 requests per minute and 1,000 requests per day.
Professional users have other options for access, including Google AI Studio and Vertex AI, both of which use pay-as-you-go pricing. Paid licenses are also available with Standard or Enterprise plans.
Customizable and extensible
Gemini CLI is fully open source under the Apache 2.0 license, so developers can inspect the code, review security, and build their own extensions. 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. Google encourages developers to help shape Gemini CLI's future by submitting bug reports, suggesting features, or contributing code on GitHub.
