Gemini CLI is an open-source tool from Google: an AI agent that lets you use Gemini models from your terminal for coding and other tasks.
In plain words
Instead of chatting in a browser, you type requests at the command line. Gemini CLI can work with files, run shell commands, search the web with Google Search and fetch pages. You can add more tools by connecting MCP servers, and a GEMINI.md file gives it lasting notes about your project. Its code is public under the Apache 2.0 licence, so anyone can inspect it or contribute.
A quick example
Imagine you open a terminal in a project folder, start Gemini CLI and ask it to explain what the code does and then add a small feature. It reads the files, proposes changes and can run commands to check them, all without leaving the command line.
Where you'll meet it
- Coding help for developers who work in the terminal.
- Scripted or automated tasks that call Gemini.
- Connecting Gemini to other tools through MCP.
Related
Sources
- Docsgoogle-gemini/gemini-cli, Google (GitHub) · read 29 Sept 2026
- DocsGemini CLI documentation, Google · read 29 Sept 2026
- DocsGemini CLI: your open-source AI agent, Google Blog · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.