LedgerLens — Invoice & Receipt Extraction AI

Overview

Manual data entry is where bookkeeping time goes to die — someone squinting at a receipt and typing the vendor, date, and total into a spreadsheet, one document at a time. LedgerLens does it for you. Drop in a whole batch of invoices and receipts — PDFs or phone photos — and Claude reads each one directly (no separate OCR software to install or train), extracting the vendor, document type, date, currency, subtotal, tax, total, and individual line items. It then assigns the best-fitting accounting category from your chart of accounts. Everything lands in a review table where you can fix any category with a dropdown, then export a clean CSV ready to import into your accounting tool. It runs on your own servers with your own Anthropic API key, so your financial documents stay under your control.

Key features

• Reads PDFs and photos of invoices/receipts directly — no OCR setup
• Extracts vendor, date, currency, subtotal, tax, total, and line items
• Auto-assigns an accounting category (editable, matches your chart of accounts)
• Batch upload — process a whole pile at once
• One-click CSV export for your accounting software
• Structured output — results are always clean and consistent
• Bring your own Anthropic API key — no per-seat limits

Specifications

Product type

Self-hosted software (source code)

License

Perpetual, modify & redistribute in your products

Backend

Python 3.12 · FastAPI

Frontend

Next.js · React (review table + CSV export)

Reads

PDF, PNG, JPG, and plain text

AI model

Claude (Sonnet by default; swappable)

Requirements

Docker + your own Anthropic API key

Delivery

License key + private source download link