DocsGPT vs OCRmyPDF

DocsGPT and OCRmyPDF share 6 technologies: Rich, pdfminer.six, uharfbuzz, pypdfium2, pillow, and Pydantic. Both are written in Python.

Read it as markdown

What they share and what sets them apart

arc53

DocsGPT

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Python18.4kRead on November 6, 2026, at commit dcf08f1What is DocsGPT built with?

Only in DocsGPT

In common

ocrmypdf

OCRmyPDF

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Python35.3kRead on November 7, 2026, at commit b457e9eWhat is OCRmyPDF built with?

Only in OCRmyPDF

  • fpdf2
  • pikepdf

Side by side

SizeLines written by people and agents, without generated ones; code files, without tests.
DocsGPT812,848 lines written1,275 code files
OCRmyPDF50,888 lines written94 code files
Who writes itA commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
DocsGPT0.3% of its commits signed by AIWith Claude Code, GitHub Copilot, Codex, and Cursor
OCRmyPDF2% of its commits signed by AIWith Aider and Claude Code
ActivityFrom GitHub and its history, on the day SeeRepo read it.
DocsGPTLast push November 6, 20265,882 commits18,360 stars
OCRmyPDFLast push October 25, 20264,300 commits35,254 stars
TestsThe files that test the code, and the share of code files a test imports.
DocsGPT1,391 test files77.3% of its code files have a test that imports them
OCRmyPDF97 test files64.9% of its code files have a test that imports them

Frequently asked questions

Which is bigger, DocsGPT or OCRmyPDF?
DocsGPT, with 812,848 lines written; OCRmyPDF has 50,888.

The proof: arc53/DocsGPT's code at commit dcf08f1

Which has more GitHub stars, DocsGPT or OCRmyPDF?
OCRmyPDF, with 35,254 stars; DocsGPT has 18,360.

The proof: ocrmypdf/OCRmyPDF on GitHub

Which has more tests, DocsGPT or OCRmyPDF?
DocsGPT, with 1,391 test files; OCRmyPDF has 97.

The proof: arc53/DocsGPT's code at commit dcf08f1

Which was updated more recently, DocsGPT or OCRmyPDF?
DocsGPT: its last push was on November 6, 2026, and OCRmyPDF's on October 25, 2026.

The proof: arc53/DocsGPT's commits on GitHub

Which has more commits signed by AI, DocsGPT or OCRmyPDF?
OCRmyPDF: an AI signed 2% of its commits, with Aider and Claude Code; in DocsGPT, 0.3%.

The proof: the commits each tool signed in ocrmypdf/OCRmyPDF

See inside your code, today.

Paste your repo and see it drawn, part by part: a medium one in under a minute.

Free, no account.

Or look inside SeeRepo's own →