This paper presents solo-learn, a library of self-supervised methods for\nvisual representation learning. Implemented in Python, using Pytorch and\nPytorch lightning, the library fits both research and industry needs by\nfeaturing distributed training pipelines with mixed-precision, faster data\nloading via Nvidia DALI, online linear evaluation for better prototyping, and\nmany additional training tricks. Our goal is to provide an easy-to-use library\ncomprising a large amount of Self-supervised Learning (SSL) methods, that can\nbe easily extended and fine-tuned by the community. solo-learn opens up avenues\nfor exploiting large-budget SSL solutions on inexpensive smaller\ninfrastructures and seeks to democratize SSL by making it accessible to all.\nThe source code is available at https://github.com/vturrisi/solo-learn.\n