AI access from the command line
Developed by Google, gemini-cli is an open-source tool that provides direct access to the Gemini AI model via the terminal. The software allows users to quickly and lightweightly create AI prompts within a command-line environment.
Updates
- October 25, 2026: Stars 108,165 → 108,179, latest release v0.65.0 (October 20, 2026).
What you get
- You can inspect and edit your codebases directly from the command line.
- You can generate new applications from images or text documents.
- You can automate your repetitive tasks with command scripts.
Installation
npm install -g @google/gemini-clibrew install gemini-cliRunning it
# Using npx (no installation required)
npx @google/gemini-cliIf you don't write code
I want to access the Gemini AI model via the terminal. Run the command 'npm install -g @google/gemini-cli' to install the tool globally on your computer using the npm package manager, or use the command '# Using npx (no installation required) npx @google/gemini-cli' to run it directly without any installation.
Repository: https://github.com/google-gemini/gemini-cli. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-10-25: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.