The open source PII and PHI redaction and de-identification engine
Examples scripts that showcase how to use Private AI Text to de-identify, redact, hash, tokenize, mask and synthesize PII in text.
Deduce: de-identification method for Dutch medical text
純前端文件去識別化工具：PDF/Word/Excel/TXT/Markdown 自動偵測個資、遮罩預覽、人工覆核、CSV 編碼表可還原，資料不出電腦
Robust de-identification of medical notes using transformer architectures
Philter redacts sensitive information such as PII and PHI in text.
Deidentify people's names and gender specific pronouns
DICOM gateway for de-identification or tag morphing
Application and python script to identify, remove, and/or recode personally identifiable information (PII) from field experiment datasets.
Identify and tokenize sensitive data automatically using Cloud DLP and Dataflow
Go library that detects personally identifiable information in text and structured data and replaces it with deterministic, format-preserving substitutes.
Terminal-native agent for clinical workflows — prior auth, coding audit, and documentation, with reviewable output
👥 An R package for deidentifying datasets that may contain personally identifiable information (PII)
NIST Collaborative Research Cycle on Synthetic Data. Learn about Synthetic Data week by week!
A local-LLM privacy layer for anything you paste into a cloud model — detect, tokenize, restore. Zero deps, reversible, strong on Chinese.
detection of burned in pixels using OCR (under development)
A python client used to interact with the Private AI's API
Privacy-preserving representations of training data for de-identification
Reversible PII masking for LLM agents: piighost replaces personal data with placeholders before the model sees it, then restores the real values in replies and tool calls. LangChain, Pydantic AI, LlamaIndex and Claude Code integrations, plus an OpenAI/Anthropic-compatible proxy.
To associate your repository with the deidentification topic, visit your repo's landing page and select "manage topics."