gemini-cli
An AI agent that brings the power of Gemini directly into your terminal by Google.
Gemini CLI is an open-source AI agent that brings Google's Gemini AI models directly into your terminal, providing developers with a powerful command-line interface for AI-assisted coding and automation. The tool offers lightweight access to Gemini's advanced reasoning capabilities with a 1M token context window, making it ideal for understanding large codebases, generating code from various inputs (including PDFs and images), and automating complex development tasks.
The CLI comes packed with built-in tools including Google Search grounding for real-time information, file operations, shell command execution, and web fetching capabilities. It supports extensibility through MCP (Model Context Protocol) for custom integrations and offers multiple authentication options including free tier access with personal Google accounts (60 requests/min, 1,000 requests/day). Advanced features include conversation checkpointing, custom context files (GEMINI.md), and GitHub Action integration for automated workflows.
Designed specifically for developers who live in the command line, Gemini CLI excels at tasks like debugging issues, querying pull requests, handling complex rebases, and running non-interactively in scripts for workflow automation. Whether you're starting a new project, analyzing existing code, or building automated CI/CD pipelines, this terminal-first tool provides the most direct path from your prompt to Google's powerful AI models.
Installation
# via Homebrew
brew install gemini-cli
# via npm
npm install -g @google/gemini-cli
# via npx
npx @google/gemini-cli
