#pii

Cisco AI Defense middleware for LangChain agents

Fast, zero-dependency redaction of secrets & PII from text and logs — in pure Rust.

Small engine of PII detector with masking and custom rules.

Zero-dependency .NET library for RAG text preparation: multilingual cleaning, sensitive data masking, content filtering, and semantic chunking across 14 languages.

Open-source data protection framework for AI agent workflows in n8n. Detects, tokenizes, and reversibly anonymizes sensitive data before it reaches your models.

Know your documents before they reach an LLM

Local, GPU-accelerated redaction for video & screen recordings — blur, black-box, or mosaic faces and/or any regex-matchable text. Human review, no cloud.

A Rust port of Microsoft Presidio — PII detection & anonymization (analyzer + anonymizer + Python bindings)

TypeScript SDK for Declaw — security-first sandboxing for AI agents

A TypeScript library for validating and securing LLM prompts — PII, jailbreak, prompt injection, profanity, toxicity and relevance guards. Zero-config defaults, extensible with custom patterns.

Monolog processor to keep sensitive data and secrets out of your logs

Free, local-first data catalog that auto-drafts your EU compliance evidence — a GDPR Art. 30 RoPA and a DORA register. One command, ~5 minutes, no Docker. Reads names and types, never the values: raw data never leaves your machine. AGPL-3.0; the paid portal adds only the signed official record — price on the page.

An ephemeral workflow engine which acts as the basis for the StyloBot, Wall & Workflow as well as the lucidRAG system

Zero-dependency PII + quality + noise audit for LLM datasets (TR/EU/US) — TypeScript/Node.js