mcp-server

gemini-cli: AI in your terminal

Name: gemini-cli: AI in your terminal
Author: google-gemini

Get AI power with gemini-cli, for founders, 105k+ GitHub stars

intermediate⏱ 1-2 hours💵 Free (self-hosted)

106,674 stars14,481 forksTypeScriptHealth Score 8/10Updated 8/25/2026100% free · open source

What it is

Use Gemini directly in your terminal to get answers and automate tasks.

What you can make with it

Automations like: when a new customer signs up on Stripe, add them to a spreadsheet and send a welcome email.

How it helps

It saves you time by integrating the power of Gemini into your workflow, making it easier to automate tasks and answer questions.

Real use case example

"A founder creating a new SaaS product wants to automatically add new customers to their spreadsheet. They can use Gemini-cli to write a custom script that queries Gemini, pulls the customer data, and updates the spreadsheet. The script runs continuously in the background, and the founder receives real-time updates on new customers."

If you're new

Beginners can pick this up when they want to dip their toes into AI and automation.

If you're senior

Senior engineers and professionals will reach for this when they need a robust and customizable integration of Gemini with their existing workflow.

Common confusion cleared up

Gemini-cli is not a Gemini web interface, but a terminal-based client that allows you to use Gemini's power in scripts and workflows.

Best inside these AI tools

CursorCodex CLI

Pairs with

Stripe webhookNotion databaseSpreadsheet apps like Google Sheets

Why we list it on WorkflowStacks: It's an open-source and free alternative to paid Gemini tools.

What it does

Gemini-cli is an open-source AI agent that allows you to interact with Gemini's AI capabilities directly from your terminal, enabling you to automate tasks, generate text, and more.

Install / run

npm install -g @gemini/cli

When to use it

•When you need to automate repetitive tasks using AI-generated text or responses
•When you want to integrate AI capabilities into your command-line workflow or scripts
•When you need to test or experiment with AI models without a graphical interface

Quick start

1Run `gemini --help` to see available commands and options
2Configure your API key by running `gemini config set api_key YOUR_API_KEY`
3Use `gemini generate` to generate text based on a prompt, such as `gemini generate --prompt 'Write a short story about AI'`
4Experiment with different models and parameters using `gemini --model MODEL_NAME --param PARAM_VALUE`

Ready-to-paste prompt

gemini generate --prompt 'Write a product description for a new smartwatch' --model 'text-davinci-002'

Heads up: You need to have a Gemini API key to use the gemini-cli tool, which can be obtained by creating a Gemini account and following the instructions in the README

Saves to your device

Topics

ai-agents

cli

gemini

gemini-api

mcp-client

mcp-server

How gemini-cli: AI in your terminal works

Codeflow

Free to inspect

Gemini-cli: AI in your terminal is a very large TypeScript project (~556k lines across 2284 code files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~556k lines · 2284 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js · Docker

No API keys detected

TypeScript 97%JavaScript 2%Python 1%

Where to start reading