DEV Community

Basant Nema
Basant Nema

Posted on

ReceiptVault: The 100% Offline AI Bookkeeper for Freelancers Under Strict NDAs

#devchallenge #hf26challenge #ai #hacktoberfest

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 2 — Side Hustle

What I Built

ReceiptVault is a zero-data-leakage, offline-first AI accounting and invoice parser designed specifically for freelancers, consultants, and boutique agencies working under strict client Non-Disclosure Agreements (NDAs).

Standard cloud accounting software either charges hefty recurring fees or relies on closed cloud AI APIs where confidential client bills, hourly rates, and project scopes risk being ingested for model training or data logging.

ReceiptVault runs quantized, open-weight language models locally on your computer. You drop receipt text or invoice OCR, and it instantly extracts line items, dates, vendor metadata, and tax categories into an audit-ready ledger with zero outbound network traffic.

Demo

The user interface provides instant local parsing, privacy badges, and one-click tax CSV export:

[ Receipt Ingestion Panel ]  -->  [ Local Quantized Model ]  -->  [ Encrypted Tax Ledger ]
      (Offline / Air-Gapped)           (Zero Cloud Telemetry)            (Audit-Ready CSV Export)
Enter fullscreen mode Exit fullscreen mode

Running locally at http://localhost:5002:

  • Categorization: Automatically flags software subscriptions, subcontractor payouts, and business expenses.
  • Privacy Assurance: 100% of data processing remains in-memory on the local host.
  • Export: Instant tax deductible summary formatted for accountants and tax season.

Code

The project is completely open source under the MIT License:

GitHub logo basantnema31 / receipt-vault

ReceiptVault 🔐

Zero-Leak, Local-AI Bookkeeping & Invoice Parser for Freelancers

Built for the Hacktoberfest Open-Source AI Challenge: Week 2 — "Side Hustle"

💼 The Problem & Why Someone Would Pay For It

Freelancers, agency owners, and independent contractors regularly sign strict Non-Disclosure Agreements (NDAs) with clients. They cannot upload confidential invoices, receipts, project milestones, or subcontractor bills to cloud LLMs (like OpenAI or Anthropic) without risking breach of contract or leaking proprietary pricing.

Yet, manual bookkeeping takes 4 to 8 hours per week and standard accounting software charges $30–$60/month.

ReceiptVault solves this with a privacy-first, offline open-weight AI architecture:

  • 🛡️ Zero Data Egress: All parsing and entity extraction runs locally using open-weight models.
  • ⚡ Automated Categorization: Classifies expenses into standard tax categories.
  • 📊 One-Click Tax Export: Generates clean, audited CSV ledger ready for accountants.
  • 💰 Monetization Viability: Freelancers happily pay a one-time $29–$49 lifetime license or $9/mo offline desktop utility…
View on GitHub

How I Built It

  • Core Engine: Lightweight Python Flask service that interfaces with local open-weight models (such as Qwen2.5-Coder and SmolLM).
  • In-Memory Ledger: Structured entity extraction capturing vendor, date, invoice IDs, subtotal, and tax rates without external database dependencies.
  • Frontend Dashboard: Clean dark-mode dashboard tailored for quick review, manual override, and bulk CSV generation.

Why Someone Would Pay For It (The Side Hustle Thesis)

Freelancers spend an average of 4 to 6 hours every month sorting receipts, matching expenses, and categorizing invoices for tax season. More importantly:

  1. NDA Compliance is Worth Real Money: Freelancers risk thousands of dollars in breach-of-contract penalties if client project invoices leak to cloud LLMs. An air-gapped solution solves this pain point completely.
  2. Predictable Pricing: A one-time $29–$49 desktop license or a modest $9/month subscription offers compelling ROI compared to SaaS platforms that cost $30–$60 every single month.

Why Does Open Innovation Matter?

Open innovation was crucial to making ReceiptVault both technically viable and economically practical:

  1. True Confidentiality: Closed API vendors cannot offer air-gapped guarantees for small desktop utilities. Open-weight models ensure that user data stays strictly on the user's hardware.
  2. Zero Marginal Inference Cost: By running on local hardware, the product incurs $0 in per-token API costs. This makes low-cost one-time licenses profitable.
  3. Model Sovereignty: Developers and users have the freedom to swap or fine-tune models to adapt to local regional tax rules without platform lock-in.

Prize Categories

  • Featured Category: Side Hustle Challenge (Primary Entry)

Built with ❤️ for Hacktoberfest 2026.

Top comments (0)