Gemini CLIAn open‑source command‑line AI agent bringing Gemini 2.5 Pro into your terminal for coding, research, content and task automation.

Gemini CLI is an open-source command-line AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving users the most direct path from their prompt to the model. The tool is designed for developers who live in the command line, offering a free tier with 60 requests per minute and 1,000 requests per day with a personal Google account. It also features powerful Gemini 3 models with improved reasoning and a 1M token context window. Gemini CLI comes with built-in tools such as Google Search grounding, file operations, shell commands, and web fetching. Additionally, it supports custom integrations through Model Context Protocol (MCP). The tool is licensed under Apache 2.0 and has a terminal-first design. In terms of installation, Gemini CLI can be run instantly with npx or installed globally using npm, Homebrew, or MacPorts. It also supports installation with Anaconda for restricted environments. The tool has multiple release channels, including preview, stable, and nightly, allowing users to choose the level of stability they prefer. The key features of Gemini CLI include code understanding and generation, automation and integration, and extensibility. It can be used to query and edit large codebases, generate new apps from PDFs or images, and automate operational tasks. Overall, Gemini CLI is a powerful tool for developers who want to leverage the capabilities of Gemini in their terminal.