Docs & PDF Q&A

pdf-craft

Rebuilds a scanned book into a readable ebook

Visit official page 日本語で詳しく見る

Popularity

★ 6.1k

Last update

August 2026

License / pricing

MIT

What it does

Converts scanned PDFs into Markdown or EPUB, recognising tables and formulas, separating body text from headers, footers and page numbers, and running the whole pipeline locally given a GPU. Recognition uses DeepSeek's open OCR model, which executes on your machine rather than calling their service — worth knowing either way. Digitising a book you own for personal use is one thing; distributing the resulting file is infringement. MIT.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

Setup difficultyEasy to start
Command lineRequired
API keyNot required
Sends data onlineNo

Judged automatically from the project's own metadata. Always confirm on the official page.

pdf-craft FAQ

Is pdf-craft free?: Yes. It runs on your own machine, so there is no usage-based cost either.
Do I need to install anything or write code to use pdf-craft?: It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
Does pdf-craft work on a phone?: No. It needs a computer.
Can I use pdf-craft commercially?: The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
pdf-craft (this page)	Required	Not needed	No	No	Yes
OCRmyPDF	Required	Not needed	No	No	Yes
Paperless-ngx	Required	Not needed	No	No	Yes
opendataloader-pdf	Required	Not needed	No	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other docs & pdf q&a tools

OCRmyPDF

Makes scanned PDFs searchable and selectable

Paperless-ngx

Digitize all your paper documents, searchable forever

opendataloader-pdf

Pulls PDF structure — tables and all — into AI-ready formats

zerox

OCR that hands each page to a vision model and gets Markdown back

Browse all tools Home

What it does

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

pdf-craft FAQ

Is pdf-craft free?

Yes. It runs on your own machine, so there is no usage-based cost either.

Do I need to install anything or write code to use pdf-craft?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does pdf-craft work on a phone?

No. It needs a computer.

Can I use pdf-craft commercially?

The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
pdf-craft (this page)	Required	Not needed	No	No	Yes
OCRmyPDF	Required	Not needed	No	No	Yes
Paperless-ngx	Required	Not needed	No	No	Yes
opendataloader-pdf	Required	Not needed	No	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.