Getting started with Gemini Command Line Interface (CLI)

Google has recently released Gemini Cli, a powerful orders tool designed for developers’ workflow fees with artificial intelligence. Whether you are working through huge code bases, hard -task automation, or creating new applications from graphics and PDFs, Gueini Cli brings multimedia intelligence to your station.

With Gemini Cli, you can:

• Inquiries and editing code code – even beyond the standard context of the distinctive 1m symbol.

• Create applications from visual inputs such as PDFS or design drawings.

• Automation of operational workflow tasks – from handling applications to retalcation management.

• Connect outer tools and MCP servers, including Imagen, Veo and Lyria to generate media.

• Use Google Search as a grounding tool, directly inside your station.

In this tutorial, we will go beyond you how to install, configure and start using Gemini Cli to enhance daily developer tasks.

JS knot installation

To start, you will need to install node.js on your system:

• Go to Nodejs.org and download the latest version of LTS.
• Stabilize.
• Use the default settings and complete the installation.

CLI installation and use

To install Gemini Cli, run the following command:

npm install -g @google/gemini-cli

Once installed, it can be prepared by running the next simple code at the station

In the first term, you will be asked to:

• Choose color theme For the Cli interface.
• Ratification With your personal Google account – this allows Gemini with generous use limits: 60 requests per minute and 1000 requests per day.

You are now ready to start using Gemini Cli to enhance your development workflow!

If you need to access a specific josphic model or want to use higher use, you can use your API key.

• Create a key from Google AI Studio.
• Set it as an environment variable at your station by operation:

export GEMINI_API_KEY="YOUR_API_KEY"

Replace your_API_KEY with the actual key you created. This Gemini Cli allows authentication to use your key instead of your Google account.

Inquire

Once everything is formed, we will test it with Ribo Gitap

Run the following thing to cloning Marktechpost Github Repo contains multiple lessons of artificial intelligence

git clone https://github.com/Marktechpost/AI-Notebooks.git
cd AI-Notebooks

Once in the AI-Notebooks folder, run the next thing to run Cli

This will call Cli

Summarize various educational programs in the warehouse

To start, to try a simple mentor:

Give an overview of the different tutorials in this repository

Gemini Cli will read the Readme.MD file – assuming that it contains details about educational programs – and create a summary summary based on that information.

Explanation of different files in a sub -folder

To refer to a specific guide or file in your demands, use a file @ Code followed by the folder or file name. Gemini Cli also supports automatic completion, so when writing @The available files and folders will be suggested automatically.

Let’s test this with the following claim:

@A2A_Simple_Agent briefly explain the different files in this folder and how they work together to implement the A2A agent. Focus only on the .py files and the README.md file

Implementation of GIT order

Gemini Cli can also implement the Shell orders directly from your demands.

How many git commits have been made so far

When such an order is running, Gemini will:

• Ask your permission before implementing it.
• Run the Shell Order safely.
• Bring the result and display it automatically.

Memory update

We can also manage the educational context of Amnesty International using /memory Order

/memory add This Git repository contains multiple self-contained tutorial projects demonstrating how to use the Gemini CLI and build agent-based systems. Each folder (e.g., A2A_Simple_Agent) focuses on a specific concept like agent communication, tool use, or integration patterns. When asked, summarize or build on individual tutorials while keeping their scope isolated.

Check statistics

the /Statistics In Gemini Cli provides a detailed summary of your current sitting. It appears main measures such as using the total symbol, any savings of temporary -stored codes (when available), and the total period of the session. This is useful for tracking use efficiency and understanding how to use the model during your workflow.

Leave

You can finish the Gemini Cli session at any time using /Leave He orders. Once you come out, CLI will display a session summary – including the total used symbols, the duration of the session, and the collapse of the distinctive icons of input and outputs.

More reading

To explore the full range of orders, check the gemini Cli orders guide. There are many powerful orders that make Gemini Cli a multi -use tool for developers. In this tutorial, we only scratched the surface to give you an essential overview of its basic features. For more details and updates, you prefer to visit the official Gemini Cli Github warehouse.

I am a graduate of civil engineering (2022) from Islamic Melia, New Delhi, and I have a strong interest in data science, especially nervous networks and their application in various fields.