# Gemini CLI > Command-line AI agent for coding, editing, querying, and automating tasks using Google Gemini models. Gemini CLI is an open-source command-line tool that brings Google’s Gemini models into your terminal. It supports code generation, editing, project scaffolding, multimodal input, tool execution, and slash-command workflows. You can use it to summarize code changes, query large codebases, refactor code, automate rebases, or even create apps from PDFs and sketches. Key features include: - Custom slash commands via TOML files - MCP integration with `/mcp` commands and tool discovery - OAuth, Vertex, and API key authentication - Shell passthrough (!), file injection (@), and vim-mode editing - Full local config and memory override support via GEMINI.md files Gemini CLI is highly extensible, supports CI/CD workflows with headless auth, and includes built-in privacy, telemetry, and version controls. ## Features - Slash commands for AI workflow management - Custom TOML-based command shortcuts - @ file inclusion and ! shell passthrough - Project-aware and git-aware context loading - OAuth and Vertex AI API key authentication - Hierarchical memory via GEMINI.md files - Tool execution and MCP server integration - Support for vim-mode editing - System settings override and telemetry export ## Integrations Gemini API, Google Vertex AI, MCP Servers, Google Workspace, Git, Local shell environment ## Platforms WINDOWS, MACOS, LINUX ## Pricing Free ## Version 0.1.15 ## Links - Website: https://geminicli.com - Documentation: https://ai.google.dev/gemini-api/docs - Repository: https://github.com/google-gemini/gemini-cli - EveryDev.ai: https://www.everydev.ai/tools/gemini-cli