Source: https://seerepo.com/r/PaddlePaddle/PaddleOCR
Markdown source: https://seerepo.com/r/PaddlePaddle/PaddleOCR.md
Description: PaddlePaddle/PaddleOCR is a C++ repo with 153,989 lines written. PaddleOCR is built with Jetpack Compose, FastAPI, core-ktx, and 3 more.

# What's inside PaddlePaddle/PaddleOCR

PaddlePaddle/PaddleOCR is a C++ repo with 153,989 lines written. PaddleOCR is built with Jetpack Compose, FastAPI, core-ktx, and 3 more. AI signed 0.3% of the 5,137 commits of PaddleOCR.

Its description on GitHub: “Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.”

C++ · Apache-2.0 · 92,256 stars · GitHub: https://github.com/PaddlePaddle/PaddleOCR

Read on November 4, 2026, at commit dab3fe3.

## More on this repo

- [What is PaddleOCR built with?](https://seerepo.com/r/PaddlePaddle/PaddleOCR/built): PaddleOCR is built with Jetpack Compose, FastAPI, core-ktx, and 3 more.
- [How much of PaddleOCR did AI write?](https://seerepo.com/r/PaddlePaddle/PaddleOCR/ai): AI signed 0.3% of the 5,137 commits of PaddleOCR.

## In figures

- 153,989 lines written: The ones people and agents wrote: product, tests, schemas and tooling. Generated code doesn’t count.
- 706 files: The same as the lines: product, tests, schemas and tooling. What’s generated doesn’t count.
- 105 test files: The files that test the code.
- 24 technologies: Each service with the file and line that prove it.

SeeRepo read the facts in its code and kept none of it. AI only helps sort its packages and folders by their names, and never sees its code.

## Frequently asked questions

### What is PaddlePaddle/PaddleOCR?

PaddlePaddle/PaddleOCR is a C++ repo with 153,989 lines written. Its description on GitHub: “Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.”

The proof: [its page on GitHub](https://github.com/PaddlePaddle/PaddleOCR)

### What is PaddleOCR built with?

PaddleOCR is built with Jetpack Compose, FastAPI, core-ktx, and 3 more.

The proof: [each service with its file and line](https://seerepo.com/r/PaddlePaddle/PaddleOCR/built)

### How much of PaddleOCR did AI write?

AI signed 0.3% of the 5,137 commits of PaddleOCR.

The proof: [the commits each tool signed](https://seerepo.com/r/PaddlePaddle/PaddleOCR/ai)

### What license does PaddleOCR have?

PaddleOCR is released under the Apache-2.0 license.

The proof: [its page on GitHub](https://github.com/PaddlePaddle/PaddleOCR)

### How many stars does PaddleOCR have on GitHub?

PaddleOCR had 92,256 stars on GitHub on November 4, 2026.

The proof: [its page on GitHub](https://github.com/PaddlePaddle/PaddleOCR)

## Add this badge to your README

It links to this page and updates itself each time SeeRepo reads the repo.

```markdown
[![PaddlePaddle/PaddleOCR on SeeRepo](https://seerepo.com/badge/PaddlePaddle/PaddleOCR.svg)](https://seerepo.com/r/PaddlePaddle/PaddleOCR?de=insignia)
```

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.