Google introduces an open-source AI coding assistant for developers
What's the story
Google has unveiled a new open-source artificial intelligence (AI) agent, Gemini CLI, to enhance developers' coding experience. The innovative tool integrates Google's Gemini AI models directly into developers' terminals. It allows natural language requests like explaining complex code sections, writing new features, debugging code, or executing commands. The company says it is a "fundamental upgrade" to the command line experience for developers.
Versatility
More than just a coding assistant
While Gemini CLI excels at coding, Google says it can do much more. The company describes it as a "versatile, local utility" that can be used for various tasks, including content generation, problem-solving, deep research, as well as task management. The tool leverages the Gemini 2.5 Pro reasoning model with a one million token context window—the amount of information an AI model can process at once.
Advanced capabilities
Gemini CLI's advanced features
Gemini CLI comes with several advanced features. It is integrated with Gemini Code Assist, has built-in Model Context Protocol (MCP) and Google Search support, and lets developers create images and videos using Veo and Imagen AI tools. The company has also made the tool available for developers to preview from today, under a free Gemini Code Assist license that can be obtained through a personal Google account.
Usage limits
Free license offers generous limits
The free license offers Gemini CLI users with a generous limit of 60 model requests per minute and 1,000 requests per day. This is the "largest allowance" offered across the industry, according to Google. However, it remains unclear if there will be any provisions for those who exceed these limits.