Google has launched a new open-source AI agent that brings Gemini’s coding, content generation, and research capabilities directly into developers’ terminals. Gemini CLI provides a “fundamental upgrade to your command line experience,” according to Google, making it easier for developers to write and debug code using natural language prompts.
“It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model,” Google said in its announcement. “While it excels at coding, we built Gemini CLI to do so 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 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). Google says the Gemini CLI agent is integrated with Gemini Code Assist, includes built-in Model Context Protocol (MCP) and Google Search support, and allows developers to generate images and video using its Veo and Imagen AI tools.
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. That provides Gemini CLI users with a usage limit of 60 model requests per minute and 1,000 requests per day, which Google says is the “largest allowance” offered across the industry.
Google hasn’t mentioned if anything is available for users who exceed those usage limits or if the AI agent will remain free when it becomes fully available. That generous allowance could give it an edge over other AI coding options like Anthropic’s Claude, GitHub Copilot, or even Microsoft’s similar AI chatbot inside Windows Terminal.
