DEV Community: IB2M_Official

Behind EcoPrompt: How I modeled the hidden physical cost of AI prompts (Zero Telemetry)

IB2M_Official — Sat, 26 Sep 2026 17:23:21 +0000

GenAI web interfaces (ChatGPT, Gemini, Claude) are pristine, minimal, and fast. But behind every single prompt lies a massive array of GPU clusters consuming real electricity, requiring evaporative cooling water, and generating carbon emissions.

I created EcoPrompt, an open-source Chrome Extension, to make this invisible footprint transparent to users in real time.

Before diving into the methodology, here is a quick 30-second promo teaser giving an overview of the concept:

(Watch on YouTube: EcoPrompt Concept Teaser)

❓ Why I Built This

Most environmental discussions around AI fall into two extremes: complete ignorance of resource consumption or overwhelming guilt trips about using modern tools.

I wanted a middle ground: unobtrusive, guilt-free awareness.

Physical Transparency: When you send a prompt, you should know if that specific request cost a teaspoon of water or a full glass.
Behavioral Nudging: Seeing real-time metrics encourages better prompting habits — batching queries, choosing lightweight models (Flash/Haiku) for simple tasks, and saving heavy reasoning models (o1/Opus) or image generation for when they are truly needed.
Financial Alignment: Bridging the gap between free web interfaces and underlying API token costs.

🔬 What Is EcoPrompt Based On?

The metrics aren't arbitrary guesses. They rely on peer-reviewed research and industry sustainability reports:

Water Consumption (Scope 1 & 2): Based on research from UC Riverside ("Making AI Less Thirsty", Li et al.), combining direct evaporative cooling at the datacenter with indirect water used for electricity generation.
Energy & Carbon Footprint: Calibrated using research from Hugging Face ("Power Hungry Processing", Luccioni et al.) alongside regional grid carbon intensity averages and provider datacenter efficiency metrics (PUE).
Tiered Model Granularity: Different model architectures are categorized into distinct compute tiers:
- Lightweight (GPT-4o mini, Gemini Flash, Claude Haiku): ~3–5 mL water / ~0.0005 kWh
- Standard (GPT-4o, Gemini Pro, Claude Sonnet): ~20–30 mL water / ~0.003 kWh
- Reasoning / Extended Thinking (o1/o3-series, Claude Opus/Thinking): ~120–250 mL water / ~0.02 kWh
- Image Generation (DALL-E 3, Imagen 3): ~250–400 mL water / ~0.035 kWh

🛡️ Privacy & Architecture Choice

Building an extension that interacts with pages like chatgpt.com or claude.ai carries a heavy privacy responsibility.

To ensure 100% user privacy:

Zero Telemetry: No tracking, no external analytics server, no remote APIs.
Client-Side Only: Character length and model types are parsed in temporary browser memory.
Local Persistence: All history and trends stay in your browser's chrome.storage.local.
Manifest V3 & Vanilla JS: Lightweight footprint with no external npm dependencies.

🔗 Try It & Explore

EcoPrompt is completely free and open-source under CC BY-NC-SA 4.0.

📦 Install from Chrome Web Store: EcoPrompt on Chrome Web Store
💻 Source Code & Documentation: GitHub Repository
☕ Support Development: Ko-fi Page

How do you approach tracking or optimizing your daily AI usage? Let's discuss in the comments!

Why I built a zero-telemetry Chrome extension to measure the physical cost of AI prompts

IB2M_Official — Tue, 08 Sep 2026 17:46:26 +0000

Every developer today relies on LLMs. Whether it's drafting boilerplate, refactoring complex logic, or debugging edge cases on ChatGPT, Google Gemini, or Claude, queries are sent dozens of times a day.

Yet the thermodynamic and compute realities of these queries remain invisible. Matrix multiplications run on energy-dense hardware, requiring massive power draw and water-cooling towers at scale.

I wanted to make this resource footprint visible without adding friction or guilt-tripping. So I built EcoPrompt — an ultra-lightweight, 100% client-side Chrome extension (Manifest V3) that calculates the environmental and financial cost of your prompts in real time.

🌿 What EcoPrompt Measures

Whenever you submit a prompt on ChatGPT, Claude, or Gemini, an unobtrusive toast notification computes:

🍃 Carbon Footprint (CO₂e): In grams and milligrams, with real-world equivalents (e.g. smartphone recharges).
💧 Water Consumption (mL): Factoring on-site data center cooling evaporation and grid-level water draw.
⚡ Active Energy (Wh): Real-time compute draw based on model architectures and Power Usage Effectiveness (PUE).
💶 API Cost: Public market token cost benchmarks.

🛠️ Architecture & Strict Constraints

Building for production while respecting developer workflows led to three zero-compromise rules:

Zero Telemetry & 100% Client-Side Privacy:
No prompt text is ever captured, saved, or routed through an external server. The extension strictly measures character length in-memory to calibrate KV-cache compute multipliers, then purges the string immediately. Everything runs inside chrome.storage.local.
Vanilla JS & Native SVG (Bundle < 150 KB):
No bloated charting libraries (no Chart.js, no D3, no npm baggage). The integrated analytics dashboard dynamically renders timelines (Day, Week, Month, Year) using a custom lightweight SVG generator.
Custom Daily Budgets & Batching Prompts:
Users can configure soft daily thresholds (prompts, CO₂, water, or energy). A subtle counter notifies you upon reaching your budget, promoting mindful prompt engineering and query batching.

🚀 Try It on the Chrome Web Store

The extension is free and available directly on the Chrome Web Store:

👉 Install EcoPrompt on the Chrome Web Store

I’d love to hear your thoughts, UI feedback, or suggestions for additional AI platforms to support!

I built UnlimBox: A Neo-Brutalist alternative to bloated corporate cloud storage clients

IB2M_Official — Sun, 06 Sep 2026 17:25:35 +0000

Most mainstream cloud storage interfaces are boring, sterile, and feel sluggish under heavy nested directories. As developers, we deserve a personal dashboard that isn't just a corporate carbon copy of Google Drive or Dropbox. I wanted something snappy, highly tactile, and visually bold.

I built UnlimBox—a fast, responsive, and secure cloud storage web app designed with a Flat Neo-Brutalist interface. It features nested folders, high-speed file uploads, secure share generation, and a fully functional Progressive Web App (PWA) wrapper for native mobile responsiveness.

Frontend: React, TypeScript, and Vite for fast builds, with Tailwind CSS driving the thick border styles.
State & Routing: React Router DOM for routing with secure client-side ProtectedRoute guards.
Backend: Express API on Node.js acting as a secure controller and authentication layer.
Database & Storage: Firebase Cloud Firestore for reactive document indexing and Firebase Auth for sessions.

Handling over 90GB of assets in early testing caused high Firestore read overhead. I solved this by flattening the folder structure query schemas to index directories on a parent-ID level and implementing a Node proxy server to cache repetitive asset metadata lookup requests.

I'd love for this community to push its limits! Check it out at https://cloud-storage-afd51.web.app/ and let me know how the tactile UI feel on your mobile device.

I built EcoPrompt: Track the real-time CO2, water & energy cost of your AI prompts

IB2M_Official — Mon, 31 Aug 2026 17:20:41 +0000

Every time we send a query to ChatGPT, Google Gemini, or Claude, high-density GPU clusters consume electricity and water for cooling. While the productivity gain is immense, the environmental footprint remains invisible.

I built EcoPrompt — an open-source, lightweight Chrome extension (Manifest V3) that calculates the CO₂, water, energy, and API cost of your AI prompts in real time, 100% locally with zero prompt tracking.

🔗 Quick Links

💻 GitHub Repo: github.com/IB2M-Official/ecoPrompt
📦 Chrome Web Store: Install EcoPrompt
☕ Support: Ko-fi (IB2M)

🌿 Key Features & Architecture

📊 4 Live Metrics: Real-time in-page toasts estimating CO₂e (g), water evaporation (mL), active energy draw (Wh), and API cost equivalents.
🎯 Daily Quotas & Smart Reminders: Set custom thresholds with progressive alerts (+1, +2 extra queries) to encourage prompt batching.
📈 Native SVG Analytics: Interactive timelines across Days, Weeks, Months, and Years without external charting libraries.
🔒 100% Local & Private: No backend, no telemetry. Prompt text is never read, stored, or transmitted — character count is evaluated in memory only for length weighting.
🪶 Zero Dependencies: Pure vanilla JS and lightweight CSS (total bundle size < 150 KB).

🚀 Try it out

The project is open-source under the CC BY-NC-SA 4.0 license. Feel free to check out the repo, star it if you find it useful, and share your feedback or benchmark ideas in the comments!

How I built a developer-first cloud drive with a "Flat Brutalist" UI 📦

IB2M_Official — Tue, 11 Aug 2026 13:46:47 +0000

Hey everyone! 👋

I’ve always been frustrated by the strict quotas of traditional cloud storage and the lack of tools for developers. You can store files, but you can't easily integrate them into your workflows without jumping through hoops.

So, I decided to spend my weekends building my own alternative: UnlimBox. Unlimbox

My goal was twofold: offer a very generous storage capacity so you never have to worry about space, and build the ultimate toolkit for devs.

🛠️ The Tech Stack & Flat Brutalism

For the frontend, I used React and Tailwind CSS. I was tired of generic corporate designs, so I went all-in on Flat Brutalism: heavy 2px black borders, no drop-shadows, and high contrast. It makes the app feel extremely lightweight and snappy.

The backend runs on Node.js and Express.

💻 Built for Developers

Aside from standard file management and an "Express Drop" mode (for sharing files instantly without an account), I focused on developer features:

Full REST API & WebDAV support
Built-in NoSQL database for your side projects
Free static web hosting
An official CLI to manage everything from your terminal

If you want to try the CLI, it's already live on npm:
npm i -g unlimbox-cli

🤔 Looking for feedback!

The project is currently in open beta. Since I'm building this solo, I would absolutely love some feedback from other developers.

You can try the web app here (no strings attached):
🔗 https://cloud-storage-afd51.web.app/

Does the Flat Brutalist UI feel intuitive to you? Have you tried deploying a file via the CLI? Let me know your thoughts or if you find any bugs! Thanks for reading.