Walk through any street in Jamshedpur, Jharkhand, and you'll find hundreds of small shop owners and hawkers running their entire business from memory — stock levels, daily sales, employee wages, profit margins. They have no tools. Notebooks get lost. Mental math fails. And at the end of the day, most don't even know if they made a profit.
These vendors are not tech-illiterate. They have smartphones. They use WhatsApp. But every existing business app is either too complex, too expensive, or only available in English.
I wanted to solve that.
Dukaan Manager is a free, offline-capable Progressive Web App (PWA) and Android app built for small shop owners and street vendors in India. It runs entirely in the browser — no server, no subscription, no data charges beyond the initial load.
Built using HTML, CSS, JavaScript, and powered by the Gemini 2.0 Flash API, it gives every small vendor access to a smart business advisor in their pocket.
Vendors can add items by name or photo. Each item stores buying price, selling price, and quantity. The app automatically calculates profit margins and flags low-stock items with colour-coded alerts.
Sales are recorded item by item, linked to which employee made the sale. The app auto-fills prices and calculates the total. Unsaved drafts survive accidental page refreshes using sessionStorage.
Add employees with their role, salary, phone number, and joining date. Mark daily attendance (present/absent) with one tap. Track total sales made by each employee across all time.
Every saved sale is stored permanently in the browser's localStorage. History is grouped by date, collapsible, and shows daily revenue and profit — clean and simple.
This is where Google AI comes in. Using the Gemini 2.0 Flash API, vendors can ask natural language questions about their business:
Gemini receives the full context — stock data, today's sales, employee info, and the last 7 days of history — and responds with practical, concise advice tailored to that specific vendor's shop.
With one tap, the entire app switches between English and Hindi (Devanagari script). Gemini also responds in whichever language the vendor prefers. This was a critical feature — most vendors in Jharkhand are far more comfortable in Hindi.
In Jamshedpur and across Tier 2 and Tier 3 India, small vendors face three core problems:
Dukaan Manager addresses all three. It's free, it works offline, it speaks Hindi, and it puts an AI advisor — powered by Google Gemini — in the hands of someone who has never had access to business intelligence before.
| Layer | Technology |
|---|---|
| Frontend | HTML5, CSS3, Vanilla JavaScript |
| AI | Gemini 2.0 Flash API |
| Storage | localStorage + sessionStorage |
| Distribution | PWA (browser) + Android APK via WebIntoApp |
| Languages | English + Hindi (Devanagari) |
No backend. No database. No cost to run. Just a single HTML file that works anywhere.
Building with the Gemini API was surprisingly powerful. By passing structured business context — stock, sales, employees — into each prompt, I could turn a general-purpose model into a shop-specific advisor. The responses were practical, local, and genuinely useful.
The biggest challenge was making the app robust for real-world use: preventing data loss, handling float arithmetic correctly, protecting against XSS, and making sure the app felt native on a ₹8,000 Android phone.
Every small vendor who uses Dukaan Manager gets:
This is what Google AI for everyone looks like.
The app is a single HTML file — open it in any browser and it works instantly.
Built with: Gemini 2.0 Flash API · HTML/CSS/JS · localStorage · PWA
By: A builder from Jamshedpur, Jharkhand, India 🇮🇳
Built as part of Google's Meet the Builders — Gen AI Academy APAC Edition