InvoiceSnap AI
An open-source local AI receipt management tool that uses OCR and a local large language model to convert receipt photos into structured expense data and export it as CSV, emphasizing privacy and a lightweight workflow.
Timeline (last 90 days)
InvoiceSnap AI is an open-source project with code publicly available on GitHub (repository Leafyte/InvoiceSnap) that converts receipt images into a structured expense table.
InvoiceSnap AI extracts four fields from receipts: merchant name, date, total amount, and expense category.
InvoiceSnap AI's backend uses the Flask framework and handles OCR processing, AI calls, data normalization, and API routing.
InvoiceSnap AI's frontend uses vanilla JavaScript for upload, table interaction, browser storage, and CSV export, with expense records stored in the browser's localStorage.
InvoiceSnap AI's workflow has two steps: first Tesseract OCR reads the receipt text, then the OCR text is sent to a Gemma model running on a local Ollama service for structured information extraction.
When a local AI request fails, InvoiceSnap AI falls back to regular expressions and keyword rules to extract information, and flags the results for users to check carefully.
After processing by the backend, InvoiceSnap AI's receipt images are not saved as application files.
The current version of InvoiceSnap AI lacks authentication, cloud sync, bank integration, automatic tax calculation, and multi-user support.
InvoiceSnap AI does not replace accounting software, nor does it provide tax advice.
InvoiceSnap AI's author plans to prioritize improving reliability, with specific directions including adding sample receipts for repeatable testing, improving date and currency detection, highlighting uncertain or missing fields, supporting PDF invoices, refining classification, and providing more detailed expense report exports.
1 more timeline events
All Facts (11)
InvoiceSnap AI's author proposes two commercialization possibilities: a free local version plus paid installation assistance, customization, or integration services; or a customized version for freelancers and small businesses with specific category and export requirements.
50%UnverifiedInvoiceSnap AI extracts four fields from receipts: merchant name, date, total amount, and expense category.
50%UnverifiedInvoiceSnap AI's backend uses the Flask framework and handles OCR processing, AI calls, data normalization, and API routing.
50%UnverifiedInvoiceSnap AI's frontend uses vanilla JavaScript for upload, table interaction, browser storage, and CSV export, with expense records stored in the browser's localStorage.
50%UnverifiedInvoiceSnap AI's workflow has two steps: first Tesseract OCR reads the receipt text, then the OCR text is sent to a Gemma model running on a local Ollama service for structured information extraction.
50%UnverifiedWhen a local AI request fails, InvoiceSnap AI falls back to regular expressions and keyword rules to extract information, and flags the results for users to check carefully.
50%UnverifiedAfter processing by the backend, InvoiceSnap AI's receipt images are not saved as application files.
50%UnverifiedThe current version of InvoiceSnap AI lacks authentication, cloud sync, bank integration, automatic tax calculation, and multi-user support.
50%UnverifiedInvoiceSnap AI does not replace accounting software, nor does it provide tax advice.
50%UnverifiedInvoiceSnap AI is an open-source project with code publicly available on GitHub (repository Leafyte/InvoiceSnap) that converts receipt images into a structured expense table.
50%UnverifiedInvoiceSnap AI's author plans to prioritize improving reliability, with specific directions including adding sample receipts for repeatable testing, improving date and currency detection, highlighting uncertain or missing fields, supporting PDF invoices, refining classification, and providing more detailed expense report exports.
50%