privacy-filter is an open-source AI model by OpenAI for token classification, designed to identify and filter private or sensitive information in text. It is compatible with popular ML libraries and can be used via API or CLI by developers and data scientists.
Privacy Filter is a Classification & entity recognition project. Automatically detecting and filtering private or sensitive information in text data. It is built as an open-source project for developers and data scientists handling sensitive text data. Privacy Filter is open source under the Apache-2.0 license. Privacy Filter is available on the web, the command line, and API.
OpenAI builds and maintains Privacy Filter, and it first shipped in 2026. Development happens publicly on GitHub with 2.5k stars and 3 commits in the last 90 days. Key capabilities include token classification, PII filtering, and transformers compatible.
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