AI Briefinggemini-cli: Open-source Gemini agent for the terminal
google-gemini/gemini-cli
About the project
An open-source AI agent that calls Gemini models directly from the terminal environment. It provides the most direct path from prompt input to model response, performing code and automation tasks without a separate IDE or web UI.
It supports querying and editing large codebases, natural language-based debugging, and app generation using multimodal inputs such as PDFs and images. By integrating with MCP servers, it enables media generation features like Imagen, Veo, and Lyria, as well as integration with external tools such as GitHub and Slack.
It runs non-interactively within scripts, making it suitable for workflow automation. It supports JSON-formatted output and streaming events, allowing easy integration into CI/CD pipelines or other automation scripts.
It offers various authentication methods, including Google OAuth, Gemini API keys, and Vertex AI. It is a tool focused on compatibility with existing models and direct accessibility within the terminal, rather than optimization for the latest Gemini models.
google-gemini/gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
TypeScript
This introduction was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report errors, attribution issues, or removal requests via Contact.