| Name | Version | Summary | date |
| vscode-copilot-controller |
0.1.6 |
Programmatically control VSCode Copilot chat panel using OCR-based UI automation |
2025-10-23 07:28:17 |
| receipt-ocr |
0.3.1 |
A package for extracting structured data from receipts. |
2025-10-20 06:47:37 |
| kreuzberg |
3.20.2 |
Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats |
2025-10-11 18:34:25 |
| mseep-kreuzberg |
3.13.4 |
Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats |
2025-09-09 03:44:56 |
| img2text-cli |
0.1.7 |
A CLI tool to extract text from images using OCR |
2025-08-31 11:21:20 |
| wizardextract |
1.0.1 |
Text extraction from PDFs, Word files, spreadsheets, and images. Local OCR with Tesseract and optional Azure Document Intelligence for text, tables, and key–value pairs. Includes page/sheet selection and a hybrid PDF mode. |
2025-08-29 12:21:44 |
| wizarddocx |
1.0.0 |
Text extraction from Microsoft Word files. Parses Word documents natively and can optionally run local OCR with Tesseract for embedded images or scanned pages. Supports page selection and bytes input. Legacy .doc is read-only and OCR is not available. |
2025-08-28 09:27:49 |
| docsray-mcp |
0.3.3 |
AI-powered document perception and analysis MCP server with intelligent provider selection |
2025-08-06 23:41:05 |
| ocr-document-converter |
3.1.0 |
Enterprise-grade OCR and document conversion tool with dual OCR engines |
2025-07-22 15:19:03 |
| trex-ocr |
1.1.0 |
Lightning-fast OCR and QR code reader for Wayland/Linux. Tesseract by default, with optional AI-powered mode. |
2025-07-13 16:22:08 |
| trex-linux |
1.0.1 |
Lightning-fast OCR tool for Wayland/Linux. Tesseract by default, with optional AI-powered mode. |
2025-07-12 18:28:05 |
| OCR-with-format |
0.12 |
Wrapper to pytesseract to preserve space and formatting |
2024-07-06 16:37:24 |