Gemini CLI
An open-source terminal agent that connects to Google's Gemini models, with a free tier for personal Google accounts, built-in tools for search, file operations and shell commands, and MCP support for custom integrations.
Gemini CLI is an open-source AI agent that brings Gemini models into the terminal, giving a direct path from a prompt to the model. It includes built-in tools for Google Search grounding, file operations, shell commands and web fetching, and supports the Model Context Protocol for connecting custom integrations, including media generation with Imagen, Veo or Lyria.
It can query and edit large codebases, generate applications from PDFs, images or sketches, debug issues in natural language, and run non-interactively in scripts for automation. Conversations can be checkpointed and resumed, and project-specific behavior can be set through GEMINI.md context files. A GitHub Action integrates it into pull request review and issue triage.
It installs with npx, npm, Homebrew, MacPorts or Anaconda, has preview, stable and nightly release channels, and offers a free tier of 60 requests per minute and 1,000 requests per day with a personal Google account. It is written in TypeScript and Apache-2.0 licensed.