Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A python library for self-supervised learning on images.
| Date | Stars |
|---|---|
| 2026-07-24 | 3786 |
| 2026-07-25 | 3786 |
| 2026-07-28 | 3789 |
| 2026-07-30 | 3789 |
| 2026-08-10 | 3792 |
| 2026-08-18 | 3794 |
| 2026-08-19 | 3794 |
| 2026-08-20 | 3795 |
| 2026-08-22 | 3795 |
| 2026-08-24 | 3796 |
| 2026-08-27 | 3798 |
| 2026-08-28 | 3799 |
| 2026-08-29 | 3800 |
| 2026-08-30 | 3800 |
| 2026-08-31 | 3801 |
| 2026-09-01 | 3802 |
| 2026-09-02 | 3802 |
| 2026-09-05 | 3801 |
| 2026-09-06 | 3802 |
| 2026-09-07 | 3802 |
| 2026-09-09 | 3802 |
| 2026-09-10 | 3804 |
| 2026-09-11 | 3806 |
| 2026-09-12 | 3806 |
| 2026-09-14 | 3808 |
| 2026-09-15 | 3809 |
| 2026-09-16 | 3810 |
| 2026-09-17 | 3812 |
| 2026-09-19 | 3812 |
| 2026-09-20 | 3814 |
Today
+2 stars today
This week
+8 stars this week
This month
+19 stars this month
Momentum
31.0
growth rate 0.21%/day
<a name="top"></a>  [](https://github.com/lightly-ai/lightly/blob/master/LICENSE.txt) [](https://github.com/lightly-ai/lightly/actions/workflows/test.yml) [](https://pypi.org/project/lightly/) [](https://pepy.tech/project/lightly) [](https://github.com/astral-sh/ruff) [](https://discord.gg/xvNJW94) [](https://x.com/LightlyAI) Lightly**SSL** is a computer vision framework for self-supervised learning. - [Documentation](https://docs.lightly.ai/self-supervised-learning/) - [Github](https://github.com/lightly-ai/lightly) - [Discord](https://discord.gg/xvNJW94) For a commercial version with more features, including Docker support and pretraining models for embedding, classification, detection, and segmentation tasks with a single command, please contact [email protected]. We've also built a whole platform on top, with additional features for active learning and [data curation](https://docs.lightly.ai/docs/what-is-lightly). If you're interested in the LightlyStudio, our all-in-one product for [data curation and labeling](https://docs.lightly.ai/studio/) on your data, check out [lightly.ai](https://www.lightly.ai). It's free to get started! ## News 🚀 * May 28, 2026 - We now have [LeJEPA](https://arxiv.org/pdf/2511.08544) support for self-supervised learning! 🧬 * March 23, 2026 - Check out our latest open-source project [LightlyStudio](https://github.com/lightly-ai/lightly-studio) to visualize, annotate, and manage your data with ease! 🔍 * April 15, 2025 - We are excited to announce that you can now leverage SSL and distillation pretraining in just a few lines of code! We've worked hard to make self-supervised learning even more accessible with our new project [LightlyTrain](https://github.com/lightly-ai/lightly-train). Head over there to get started and supercharge your models! ⚡️ <p> <a href="https://github.com/lightly-ai/lightly-train"><img src="https://storage.googleapis.com/lightly-public/train/lightlytrain_standard_horizontal_dark.png" alt="LightlyTrain" height="40"/></a> <span> </span> <a href="https://github.com/lightly-ai/lightly-studio"><img src="https://storage.googleapis.com/lightly-public/studio/lightlystudio_standard_horizontal_dark.png" alt="LightlyStudio" height="40"/></a> </p> ## Features This self-supervised learning framework offers the following features: - Modular framework, which exposes low-level building blocks such as loss functions and model heads. - Easy to use and written in a PyTorch-like style. - Supports custom backbone models for self-supervised pre-training. - Support for distributed training using PyTorch Lightning. ### Supported Models You can [find sample code for all the supported models here.](https://docs.lightly.ai/self-supervised-learning/examples/models.html) We provide PyTorch, PyTorch Lightning, and PyTorch Lightning distributed examples for all models to kickstart your project. **Models**: | Model | Year | Paper | Docs | Colab (PyTorch) | Colab (PyTorch Lightning) | |----------------|------|-------|------|-----------------|----------------------------| | MoCo | 2019 | [paper](https://arxiv.org/abs/1911.05722) | [docs](https://docs.lightly.ai/self-supervised-learning/examples/moco.html) | [](https://colab.research.google.com/github/lig
Excerpt of 40,500 characters
Read on GitHub
327
Igor Susmelj · Lightly · Switzerland
265
248
Lightly · Switzerland
206
68
34
33
31
28
24
21
18
Saurav Maheshkar · United Kingdom
16
fruet
15
11
7
Nirbhai Singh
6
Ersi Simou
6
5
Adam J. Stewart · Technical University of Munich · Germany
5
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2c53e5ec1dcf5dea, topic:deep-learning, topic:pytorch, readme:distributed training
matched fp:2c53e5ec1dcf5dea, topic:computer-vision, readme:computer vision
matched fp:2c53e5ec1dcf5dea, topic:embeddings, topic:contrastive-learning