Testing Open Source Cluely (That help you cheat on everything with AI)

Discover how to install and test open-source Cluely, the AI that assists in interviews. This beginner’s guide covers setup, mock testing, and ethics!

Audrey Lopez

Audrey Lopez

18 June 2025

Testing Open Source Cluely (That help you cheat on everything with AI)

Curious about Cluely, the AI tool that’s got everyone buzzing for its sneaky real-time assistance? This open-source gem claims to “help you cheat on everything” by whispering answers during interviews, calls, or even exams. I set up the open-source version in ~20 minutes, and it’s wild—though ethically dicey! In this tutorial, I’ll show you how to install Cluely from GitHub, test it with a mock interview, and explore its AI magic. Buckle up, but let’s talk ethics too—Cluely’s power comes with responsibility.

💡
Want a great API Testing tool that generates beautiful API Documentation?

Want an integrated, All-in-One platform for your Developer Team to work together with maximum productivity?

Apidog delivers all your demands, and replaces Postman at a much more affordable price!
button

What is Cluely? The AI That Sees All

Cluely is an AI-powered desktop app that monitors your screen and audio, delivering context-aware answers in real time via a hidden overlay. Marketed as an “undetectable” assistant for interviews, sales calls, or even exams, it’s built for deception, sparking heated debate. Here’s the scoop on Cluely:

cluely official website

Online users hype Cluely as a game-changer for interviews, but its “cheat on everything” tagline raises red flags. Want to test it? Let’s dive in

Why Test Open-Source Cluely?

The open-source Cluely (from github.com/Prat011/free-cluely) lets you tinker with its code for free, unlike the official app’s subscription. Benefits include:

I tried it for a mock interview, and it was scarily good—but use it wisely, folks!

How to Install and Test Open-Source Cluely: Step-by-Step Guide

Ready to test Cluely? We’ll install the open-source version from GitHub and run a mock interview to see it in action. You’ll need Node.js (≥18), npm or yarn, and a Google Gemini API key. Let’s go!

1. Prerequisites

node --version
npm --version
git --version

Install via sudo apt install git (Ubuntu) or equivalent.

2. Clone the Cluely Repository

Open your terminal and clone the open-source Cluely:

git clone https://github.com/Prat011/free-cluely.git
cd free-cluely

This downloads the source code (~10 MB, took a few seconds).

3. Set Up Environment Variables

Create a .env file in the project root:

touch .env

Edit it (e.g., with nano .env) and add your API key:

GEMINI_API_KEY=your_google_gemini_api_key_here

Save and exit. This connects Cluely to Google Gemini for AI responses.

4. Install Dependencies

Install Node.js packages:

npm install

Or with yarn:

yarn install

5. Run the Cluely App

Start the development server on port 5180:

npm run dev --port 5180

Or:

yarn run dev --port 5180

Open a new terminal and launch the Electron app:

NODE_ENV=development npm run electron:dev
$env:NODE_ENV = 'development'; npm run electron:dev

Cluely opens at http://localhost:5180 and launches a desktop window. Grant screen/audio permissions when prompted. It’s stealthy—screenshots won’t show Cluely’s overlay

open source cluely

6. Test Cluely with a Mock Interview

Let’s see Cluely shine (or cringe) in a mock data scientist interview using ChatGPT’s desktop app as the interviewer. Here’s how:

Set Up ChatGPT Interview:

I'm applying for a position as a Data Scientist, and I want you to play the role of the job interviewer. Press me about my CV because you doubt my ability. Ask tough questions, and the interview will begin when I say "start Interview." Understand?

Run Cluely in Voice Mode:

testing cluely

Example:

cluely question 1 response
cluely question 2 response

Note: Cluely stays invisible during screen shares, so it’s undetectable in Zoom or Teams. I tested with my phone’s camera, as screenshots hide Cluely.

It felt like having a secret coach—super helpful, but kinda shady!

Summary:

StepAction
1Clone the repo
2Create .env with API keys
3Install dependencies (npm install)
4Run the app locally (npm run dev --port --5180)
5Grant permissions and use Cluely

Troubleshooting Cluely Issues

lsof -i :5180
kill [PID]

Or change the port in npm run dev --port 5181.

Ethics and Risks of Using Cluely

Cluely’s power is undeniable, but it’s a double-edged sword. Its “cheat on everything” vibe has sparked backlash:

Test Cluely in mock scenarios, not high-stakes settings. Users warn: “The future of lying” comes at a cost.

Customizing and Extending Cluely

Level up your Cluely setup:

I tweaked the overlay to be less intrusive—felt like a hacker!

Why Cluely is a Controversial AI Powerhouse

Open-source Cluely is a fascinating (and scary) glimpse into AI’s potential to augment—or deceive. Its stealthy design outshines basic chatbots, but the ethical minefield is real. Compared to paid Cluely (cluely.com), the open-source version offers freedom to experiment safely. The repo’s maintainer is inactive, so rely on community PRs for updates.

Ready to test Cluely? Spin it up, try that mock interview, and share your thoughts—but keep it ethical, folks!

💡
Want a great API Testing tool that generates beautiful API Documentation?

Want an integrated, All-in-One platform for your Developer Team to work together with maximum productivity?

Apidog delivers all your demands, and replaces Postman at a much more affordable price!
button

Explore more

Getting Started with the LINE MCP Server

Getting Started with the LINE MCP Server

Learn how to install the LINE MCP server and connect AI agents to LINE’s Messaging API. This guide covers setup, configuration, and testing for AI-driven chatbots.

8 July 2025

A Beginner's Guide for Google MCP Toolbox for Databases

A Beginner's Guide for Google MCP Toolbox for Databases

An Introduction to the MCP Toolbox The MCP Toolbox is a free tool from Google that helps your AI applications talk to your databases. Think of it as a special translator. Your AI can ask for information in a simple way, and the MCP Toolbox translates that request into the language your database understands, like SQL. It uses something called the Model Context Protocol (MCP), which is just a standard set of rules for this kind of communication. 💡Want a great API Testing tool that generates bea

7 July 2025

Google Gemini API Batch Mode is Here and 50% Cheaper

Google Gemini API Batch Mode is Here and 50% Cheaper

Google's Gemini API now features Batch Mode, a transformative update designed for large-scale, asynchronous tasks that comes with a 50% reduction in cost. 🚀 * This powerful endpoint allows you to process enormous jobs with your results delivered within 24 hours, all at half the standard API price. * The system is engineered for high-throughput workloads, accommodating up to 2GB JSONL files and leveraging optimizations like Context Caching for greater efficiency. * It also supports built-in

7 July 2025

Practice API Design-first in Apidog

Discover an easier way to build and use APIs