PaddleOCR license, foundation and stars
ML frameworks · Apache 2.0 (open source) · 90,195 stars
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.
License history
LICENSE fileApache 2.0 No license change recorded since the repository was created in 2020.
Latest release
No GitHub releases published; the project releases elsewhere (tags or its own site).
More in ml frameworks
| Project | Stars | |||
|---|---|---|---|---|
 TensorFlowGoogleApache 2.0 | Apache 2.0 | 200k | +538 | v2.21.0Mar 6, 2026 |
 TransformersHugging FaceApache 2.0 | Apache 2.0 | 167k | +652 | v5.17.0Sep 9, 2026 |
 whisperOpenAIMIT | MIT | 110k | - | - |
 PyTorchPyTorch FoundationBSD-style | BSD-style | 103k | +187 | v2.14.0Sep 2, 2026 |
 opencvApache 2.0 | Apache 2.0 | 91k | - | - |
 unslothApache 2.0 | Apache 2.0 | 76.7k | - | - |
 tesseractApache 2.0 | Apache 2.0 | 76.7k | - | - |
 LlamaFactoryApache 2.0 | Apache 2.0 | 75k | - | - |
About and history
- Repository
- PaddlePaddle/PaddleOCR · created May 8, 2020
- Website
- paddleocr.com
- Language
- Python
- Foundation
- None; run by its maintainers
- GitHub detects
- Apache-2.0
- Stars per week
- From the second weekly snapshot
Weekly snapshots
| Week of | Stars | |
|---|---|---|
| Sep 21, 2026 | 90,195 |
Changes
| What changed | |
|---|---|
| Sep 25, 2026 | TrackedAdded: PaddlePaddle/PaddleOCR |