privacy-filter-nemotron is an open model for token classification that detects personally identifiable information in text. It supports privacy filtering and redaction workflows through the Transformers library and can be run locally by developers.
In the Other AI space, Privacy Filter Nemotron takes a focused approach. It focuses on detecting and redacting personally identifiable information from text before it is stored or shared. It is built as an open-source project for developers building privacy and data-processing systems. The project is open source (Apache-2.0). It runs on the command line, and it can be self-hosted.
It is developed by OpenMed, and it first shipped in 2025. Development happens publicly on GitHub with 5k stars and 3k commits in the last 90 days. Key capabilities include PII detection, named entity recognition, and privacy filtering.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do