#35 · Primary category： Self-Hosted File Processing & Conversion
docstrange
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
Project last updated：10/31/25
GitHub Stars
1.5K
Forks
136
Contributors
8
License
MIT
Why we included this project
DocStrange is a single tool for turning messy source documents into clean text that downstream systems can actually consume. It takes PDFs, images, scanned pages, Word, PowerPoint, Excel files, and URLs and outputs Markdown, JSON, CSV, or HTML, with table-heavy layouts formatted so LLMs can read them properly. The OCR handles image-only and scanned documents, and the structured extraction mode accepts a field list or JSON schema to pull out specific data instead of dumping raw text. There is a built-in local web UI for drag-and-drop work, while the Python package and an MCP server for Claude Desktop make it easy to drop into an existing pipeline. If you want documents to stay on your own machines, everything can run locally on CPU or GPU with no data sent anywhere.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
immich
High performance self-hosted photo and video management solution.
paperless-ngx
A community-supported supercharged document management system: scan, index and archive all your documents
lossless-cut
The swiss army knife of lossless video/audio editing
lux
👾 Fast and simple video download library and CLI tool written in Go
excelize
Go language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets