Source: https://seerepo.com/compare/google-ai-edge/gallery/vs/PaddlePaddle/PaddleOCR
Markdown source: https://seerepo.com/compare/google-ai-edge/gallery/vs/PaddlePaddle/PaddleOCR.md
Description: gallery and PaddleOCR share 5 technologies: Jetpack Compose, core-ktx, lifecycle-runtime-ktx, ui-graphics, and coil-compose. gallery is written in Kotlin and PaddleOCR in C++.

# gallery vs PaddleOCR

gallery and PaddleOCR share 5 technologies: Jetpack Compose, core-ktx, lifecycle-runtime-ktx, ui-graphics, and coil-compose. gallery is written in Kotlin and PaddleOCR in C++.

- [google-ai-edge/gallery](https://seerepo.com/r/google-ai-edge/gallery): A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
- [PaddlePaddle/PaddleOCR](https://seerepo.com/r/PaddlePaddle/PaddleOCR): 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.

## What they share and what sets them apart

- In common: Jetpack Compose, core-ktx, lifecycle-runtime-ktx, ui-graphics, coil-compose
- Only in gallery: androidx.hilt:hilt-navigation-compose, androidx.navigation:navigation-compose, androidx.datastore:datastore, Firebase, com.google.dagger:hilt-android, lifecycle-process, androidx.media3:media3-ui, androidx.camera:camera-view, androidx.core:core-splashscreen, androidx.compose.material:material-icons-extended, net.openid:appauth, com.google.mediapipe:tasks-vision, io.modelcontextprotocol:kotlin-sdk, com.google.mlkit:genai-prompt, androidx.exifinterface:exifinterface, com.halilibo.compose-richtext:richtext-commonmark
- Only in PaddleOCR: FastAPI, lmdb, uvicorn, fastmcp, AIOHTTP, fonttools, appcompat, constraintlayout, albucore, ONNX, onnxruntime, onnxruntime-android, onnxruntime-objc, OpenCV, opencv-contrib-python, PaddlePaddle, sentencepiece, opencv-python, paddleslim, paddlex, paddleocr, albumentations, MCP, paddlenlp, scikit-image, LangChain, pypandoc, python-docx, pillow, puremagic, beautifulsoup4, Pydantic, @techstark/opencv-js, onnxruntime-web, js-yaml

## Side by side

| | gallery | PaddleOCR |
|---|---|---|
| Size | 162,164 lines written, 534 code files | 148,011 lines written, 634 code files |
| Who writes it | 0% of its commits signed by AI | 0.3% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 16, 2026, 742 commits, 25,308 stars | Last push September 16, 2026, 5,137 commits, 92,785 stars |
| Tests | 1 test files. 0.6% of its code files have a test that imports them | 105 test files. 11.4% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, gallery or PaddleOCR?

gallery, with 162,164 lines written; PaddleOCR has 148,011.

The proof: [google-ai-edge/gallery's code at commit b3e9913](https://github.com/google-ai-edge/gallery/tree/b3e9913625e93342b1a62a9ea247b3ff07c045d6)

### Which has more GitHub stars, gallery or PaddleOCR?

PaddleOCR, with 92,785 stars; gallery has 25,308.

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

### Which has more tests, gallery or PaddleOCR?

PaddleOCR, with 105 test files; gallery has 1.

The proof: [PaddlePaddle/PaddleOCR's code at commit dab3fe3](https://github.com/PaddlePaddle/PaddleOCR/tree/dab3fe35379033fdcb2d0e9572fac0b36c9a9ebf)

### Which was updated more recently, gallery or PaddleOCR?

gallery: its last push was on November 16, 2026, and PaddleOCR's on September 16, 2026.

The proof: [google-ai-edge/gallery's commits on GitHub](https://github.com/google-ai-edge/gallery/commits)

### Which has more commits signed by AI, gallery or PaddleOCR?

PaddleOCR: an AI signed 0.3% of its commits, with Claude Code, Cursor, and GitHub Copilot.

## Sources

- google-ai-edge/gallery: Read on November 16, 2026, at commit b3e9913 (https://github.com/google-ai-edge/gallery/tree/b3e9913625e93342b1a62a9ea247b3ff07c045d6)
- PaddlePaddle/PaddleOCR: Read on November 17, 2026, at commit dab3fe3 (https://github.com/PaddlePaddle/PaddleOCR/tree/dab3fe35379033fdcb2d0e9572fac0b36c9a9ebf)

## 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.
