Udhaar Khata: The Notebook Behind the Counter

Description and use

Udhaar Khata is a digital ledger that lets small businesses in India quickly and privately record customer debts using local AI, replacing traditional handwritten notebooks.

Problem

Small businesses in India rely on handwritten notebooks to track customer debts, but these notebooks can be lost, amounts disputed, and payment dates forgotten.

Outcome

Udhaar Khata enables quick, privacy‑preserving credit ledger entries with local AI inference, reducing friction compared to traditional notebooks and avoiding third‑party data sharing.

Workflow

• Enter transaction in Hindi/Hinglish/English
• Local AI model interprets sentence and returns structured JSON
• Application validates output and flags missing/malformed fields
• Proposed transaction is displayed for review and editing
• User confirms and saves entry
• Optional WhatsApp deep link opens pre‑filled payment reminder

Evidence

In almost every kirana store in India, there is a thin notebook next to the cash box. Page after page, it records entries like Ramesh ₹500, Sita ₹300, and Amit ₹1,000 baaki.

Source

I built Udhaar Khata, a privacy-focused digital ledger that lets users record transactions in everyday language instead of filling out forms.

Source

The application uses browser-side storage for ledger records and is hosted as a static website on Render, with the source code maintained on GitHub.

Source

Udhaar Khata uses an open-weight language model running directly in the browser through WebLLM and WebGPU.

Source

The model proposes a transaction, but the shopkeeper makes the final decision. This human-in-the-loop approach is particularly important when AI is handling financial information.

Source