Summary

LexNLP is one of the earliest open source legaltech projects and possibly one of the most successful. Its repository on GitHub should soon surpass 500 stars, indicating an active and popular project (and certainly one of, if not the most popular legal tech projects). It's also received some attention outside of the legal world. For example, the popular data science website towards data science published a comprehensive post covering some basic use-cases and guidance on how to use the library.

Since this is a Python library, you will need some coding skills to use it. Simple tasks like tokenization (splitting text into sections, sentences, words, etc.) or named entity recognition will be fairly straightforward, but not all of the functions are documented and you will probably need to refer to the source code sooner rather than later. If you're looking to dip your toes in the water, consider Addleshaw Goddard's microservice wrapper which exposes the underlying LexNLP functionality via a REST API.

This is an incredibly powerful tool and a must-have in any legal engineer's toolkit.