microsoft/analysing_pii_leakage

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.

Examples scripts that showcase how to use Private AI Text to de-identify, redact, hash, tokenize, mask and synthesize PII in text.

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.

Code repository for the paper "Mission: Impossible Language Models."

Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.

Differentially-private transformers using HuggingFace and Opacus

Install and use compiled privacy-filter.cpp binaries from Laravel applications.

DataCloak is a local-first sensitive-data protection layer for AI prompts.