Find sensitive data with Machine Learning techniques

Built on open source technologies

RedataSense is free and opensource, built on top of opensource technologies like OpenNLP.

Tested and already deploy in complex production environments.

Scan all your datasources

Find all sensitive data inside documents (Word, Excel, PowerPoint, text)  and databases (Oracle, SQLServer, MySQL, etc)

Machine Learning using Natural Language Processing

Named-Entity recognition (NER), Dictionary Based Search and other Natural Language Processing techniques are used

GDPR Data Discovery

It was developed with GDPR in mind, so you can know what data is Personal Information and sensitive.

A little bit of history and tech


RedataSense was born after the fork of DataDefender (a opensource project for find sensitive data and anonymization) but followed a different direction with special focus on searching and find sensitive production data using several techniques based on Natura Language Processing.

RedataSense is opensource and maintained and by


We would love to receive your feedback, good or bad!