# Document Extraction Hub

> Pay-per-page document extraction and OCR: PDF or picture in, structured JSON out, with a source reference behind every field.

- **Domain**: `doc.halowerk.com`
- **Provider**: Die Netzhandwerker (https://netzhandwerker.de)
- **A2A protocol version**: 0.2.9
- **Kind**: paid_api
- **Live-responds (last probe)**: False
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 78%
- **Payment protocol**: x402 · network `eip155:8453`
- **Wallet**: `0x2880edfff13100677bf97a3cbdf3bc34771c4e5e`

## Skills
- **extract document** — Turn one PDF into structured JSON: header fields, tables as rows and columns, key value pairs and per page full text, each field with its page, position and con
- **ocr read** — Read a picture, a scan or a screenshot: full text in reading order, typed blocks with their box on the page, tables as a matrix plus markdown, and every QR code

## URLs
- Agent card: https://doc.halowerk.com/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/doc.halowerk.com
- Documentation: https://doc.halowerk.com