Google launches Gemini CLI, an open-source AI agent for terminal developers

Google has launched Gemini CLI, an open-source AI agent that brings Gemini’s coding, content generation, and research capabilities directly to the terminal. Designed to enhance the command-line experience, it lets developers interact with the Gemini 2.5 Pro model using natural language prompts for tasks like writing, debugging, and problem-solving. The model supports a 1 million token context window, offering advanced reasoning and broader context handling.

Gemini CLI is integrated with Gemini Code Assist, the Model Context Protocol (MCP), and /software/google-search/about/, enabling deeper contextual responses and access to real-time information. It also supports media generation via Google Imagen and Google Veo, allowing users to generate images and video directly from the terminal.

The tool is available for free through a personal Google account and includes a Gemini Code Assist license. Users can make up to 60 model requests per minute and 1,000 per day, currently the highest free allowance in the industry.