Gemini CLI

Gemini CLI is an open-source AI agent that brings the power of Google's Gemini models directly into your terminal, enabling developers to build, debug, and deploy with AI assistance. It provides a lightweight and direct path from your prompts to the model.

Key Features

• Direct access to powerful Gemini models, including Gemini 2.5 Pro with a 1M token context window, available directly from the command line.
• Built-in tools for enhanced AI interactions, such as Google Search grounding, file operations, shell commands, and web fetching.
• Flexible authentication options supporting free-tier Google OAuth, Gemini API keys, and Vertex AI for individual developers and enterprise teams.
• Advanced capabilities for code understanding, generation, and debugging, allowing users to query large codebases, generate new applications, and troubleshoot issues.
• Extensible architecture with Model Context Protocol (MCP) support for custom integrations and advanced automation, including media generation.
• Seamless integration with GitHub workflows via a dedicated GitHub Action for automated pull request reviews, issue triage, and on-demand assistance.
• Non-interactive and streamable output formats (JSON, stream-json) for scripting and robust workflow automation.