ReceiptSorter: receipts in, expense sheet out, with open models on your own laptop

Description and use

ReceiptSorter automates receipt and invoice processing locally using open-weight models, saving time and keeping data private.

Problem

Freelancers and small accountants spend hours renaming receipt files, retyping totals, and guessing categories each month-end.

Outcome

ReceiptSorter automates receipt parsing locally, reducing manual bookkeeping time and keeping sensitive data on the user's laptop.

Workflow

• Clone the repo
• Run python3 webapp.py to start local server
• Open http://127.0.0.1:8765 and drag receipts or click "Try sample receipts"
• Edit any incorrect fields in the table
• Download CSV or ZIP of sorted receipts

Evidence

ReceiptSorter turns a pile of receipts and invoices into a clean expense CSV. You drop in text files, PDFs or phone photos of receipts, and open-weight models running on your own computer read each one and pull out the vendor, date, total, currency and an expense category.

Source

For the AI part, install Ollama and pull the models once: ollama pull qwen2.5:7b-instruct # text and PDF receipts ollama pull qwen2.5vl:7b # photos of receipts

Source

The server only listens on your own computer and works offline.

Source