Gemini CLI is an open-source (Apache 2.0) AI agent that brings Gemini models directly into the terminal. It provides the most direct path from your prompt to the model, pairing Gemini's reasoning with your local developer environment.
It can query and edit large codebases, generate apps from PDFs, images or sketches using multimodal capabilities, debug and troubleshoot in natural language, and automate operational tasks such as handling pull requests or complex rebases. Built-in tools cover file operations, shell command execution, web fetching and Google Search grounding for real-time information.
Gemini CLI is extensible through the Model Context Protocol (MCP), allowing custom integrations and tool servers. It offers a free tier (60 requests per minute and 1,000 requests per day with a personal Google account) with access to Gemini 3 models and a 1M token context window, plus a non-interactive mode for scripts and workflow automation.
