OpenInvoice
github.com
What it is
OpenInvoice extracts structured information from PDF and image invoices, then lets users check the results against the source document, correct fields, and export CSV or JSON. It identifies supplier and client details, invoice number, date, totals, tax, currency, SIRET, VAT number, client number, and line items. Processing starts with regular-expression patterns and invoice2data templates, using a MiniMax M2.7 language model only when required fields remain missing. The project lists English, French, German, and Swiss formats and more than 190 vendor templates. Its dashboard tracks processing volume, success rates, supplier distribution, and language-model costs. The API covers extraction, webhook ingestion, document management, CSV export, dashboard statistics, and quality metrics. Typical connections include Microsoft Teams, Outlook or email through Power Automate, OneDrive or SharePoint, and webhooks. OpenInvoice can run on customer infrastructure and connect to ERP, accounting, Microsoft 365, and email systems. The code is free and open source; deployment, integration, and ongoing support are paid services.
Spec sheet
- Purpose
- OpenInvoice extracts structured data from PDF or image invoices.Read 9 Oct 2026 · github.com
- Deployment
- The maker describes deploying OpenInvoice on a customer's infrastructure and integrating it with ERP, accounting, Microsoft 365, and email ingestion systems.Read 9 Oct 2026 · github.com
- API
- The documented API supports invoice extraction, webhook ingestion, document management, CSV export, and dashboard statistics and quality metrics.Read 9 Oct 2026 · github.com
- Integrations
- Typical integrations listed are Microsoft Teams, Outlook or email via Power Automate, OneDrive or SharePoint, and webhook ingestion.Read 9 Oct 2026 · github.com
- Authentication and database
- Clerk authentication is optional and the project lists SQLite as the default database with PostgreSQL as an option.Read 9 Oct 2026 · github.com
- Dashboard
- The dashboard tracks volume, success rates, supplier distribution, and LLM costs.Read 9 Oct 2026 · github.com
- Extracted fields
- It extracts supplier, client, invoice number, date, total, tax, currency, SIRET, VAT number, client number, and line items.Read 9 Oct 2026 · github.com
- Languages and templates
- It lists English, French, German, and Swiss invoice formats, plus more than 190 vendor-specific templates.Read 9 Oct 2026 · github.com
- License and support
- The code is described as free and open source, while deployment, integration, and ongoing support are offered as paid services; inquiries go to [email protected].Read 9 Oct 2026 · github.com
- LLM cost
- The README estimates the MiniMax LLM fallback at about $0.001 per invoice and says most invoices resolve through earlier layers with no LLM cost.Read 9 Oct 2026 · github.com
- Processing pipeline
- Extraction cascades through regex patterns, invoice2data templates, and a MiniMax M2.7 LLM fallback when required fields are missing.Read 9 Oct 2026 · github.com
- Review and export
- Users can review and correct extracted fields alongside the original document and export data to CSV or JSON.Read 9 Oct 2026 · github.com
- Runtime requirements
- The quick start lists Python 3.11+, Node.js 18+, Tesseract OCR, and poppler-utils as prerequisites.Read 9 Oct 2026 · github.com
Plans and prices
Strong points and limits
Strong points
- Extracts detailed invoice fields
- Supports line-item extraction
- Review and correction before export
- More than 190 vendor templates
- API and webhook capabilities
Limits
- Deployment and support cost extra
- Requires Python, Node.js, Tesseract, and poppler
- Language-model fallback can incur per-invoice cost
- Self-hosted setup requires infrastructure
Who it suits
OpenInvoice suits organizations processing invoices who need reviewable OCR or AI extraction, line-item data, exports, and API workflows. It is aimed at teams able to provide the listed Python, Node.js, OCR, and poppler prerequisites.
Verdict
OpenInvoice offers a free codebase for invoice extraction with layered processing, review, exports, integrations, and API access. Businesses should account for runtime prerequisites and separate paid deployment or support services.
Where Specifiction places it
- NES Emulators#16 of 267.3
- Invoice Processing Software#21 of 307.4