Google has released Gemini CLI, an open-source AI coding tool designed for terminal use. This new tool allows developers to access Gemini's AI capabilities directly from their command line, supporting tasks such as code generation, debugging, and task automation. Gemini CLI is powered by Gemini 2.5 Pro, providing access to a 1 million token context window. During the preview phase, users can make up to 60 requests per minute and 1,000 requests per day.
Gemini CLI is available under the Apache 2.0 license, encouraging community contributions for bug fixes, feature suggestions, and security improvements. It integrates with Gemini Code Assist, ensuring seamless transitions between terminal and IDE-based AI workflows. The tool also supports the Model Context Protocol (MCP) and bundled extensions, allowing for customisation and expanded functionality. Google aims to make AI-powered assistance a natural part of developers' daily workflows with this release.