thoughtbot/top_secret
Filter sensitive information from free text before sending it to external services or APIs, such as chatbots and LLMs.
This helps operations engineers, data privacy officers, or anyone managing customer interactions to automatically remove sensitive personal data from free text before it's sent to external tools like chatbots or AI models. You provide raw text that might contain things like credit card numbers, emails, phone numbers, or names, and it outputs a version of that text with the sensitive details replaced by placeholders. This ensures compliance and protects user privacy when interacting with third-party services.
327 stars.
Use this if you need to automatically sanitize free-form text inputs to protect personal identifiable information (PII) before it leaves your system.
Not ideal if you need a solution for structured data redaction, or if you require an extremely high-performance solution for massive, real-time data streams where model loading time is a critical concern.
Stars
327
Forks
8
Language
Ruby
License
MIT
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/thoughtbot/top_secret"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DataFog/datafog-python
Python SDK for PII detection and redaction in text and images, combining regex + NLP pipelines...
vmenger/deduce
Deduce: de-identification method for Dutch medical text
aphp/eds-pseudo
EDS-Pseudo is a hybrid model for detecting personally identifying entities in clinical reports
seanpedrick-case/doc_redaction
Redact PDF/image-based documents, Word, or CSV/XLSX files using a graphical user interface....
martincjespersen/DaAnonymization
Simple customizable pipeline tool for anonymizing Danish text.