Cost / License
- Subscription
- Proprietary
Since
- Since 2024
Australia








Local in-browser financial statement workspace with mathematical balance reconciliation, WebAssembly OCR, and multi-sheet spreadsheet editing.




Pull tables out of PDFs into CSV, Excel or JSON. Free, open source, runs on your own computer, no API key. Also works as an MCP server for AI assistants.


docext is a powerful tool for extracting structured information from documents such as invoices, passports, and other forms. It leverages vision-language models (VLMs) to accurately identify and extract both field data and tabular information from document images.

AI-driven tool for converting scanned PDFs, photos, and handwritten pages into structured rows and columns, exporting to Excel, CSV, or JSON, with no templates needed.


Detect and export HTML tables to CSV, Excel, JSON, NDJSON or SQL. Automatic cleaning, reusable profiles, and 100% local processing: your data never leaves your browser.




Converts PDF price lists, catalogues, invoices, and bank statements into Excel or CSV, remembers each supplier’s layout, batch processes files, and supports OCR.



Docsumo's PDF table extractor is a life-saviour when you need to analyze or store data quickly from PDF documents. Docsumo extracts tables from scanned or regular PDF files in a matter of seconds and lets you download and store data in tabular form.

Perlecta converts photos, screenshots and PDF tables into editable Excel files in seconds. Unlike typical OCR tools, it tells you what it could not read: cells it is unsure of are highlighted yellow and unreadable cells orange, so you know exactly what to check instead of...


A REST API and a hosted MCP that turn PDFs into clean, LLM-ready Markdown for agents and RAG. Own engines (MinerU, Docling), real tables, formulas and OCR. Web app and Chrome extension too.



