thoughtbot/top_secret
Filter sensitive information from free text before sending it to external services or APIs, such as chatbots and LLMs.
Combines regex-based pattern matching with named entity recognition (NER) via MITIE to detect both structured data (credit cards, emails, SSNs) and contextual information (person names, locations). The Ruby gem exposes a fluent API returning filtered text alongside a reversible mapping of redacted values, and supports disabling NER entirely for regex-only filtering when the model dependency is unavailable.
327 stars.
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
martincjespersen/DaAnonymization
Simple customizable pipeline tool for anonymizing Danish 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....