The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails.
-
Updated
Jun 25, 2025 - Python
The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails.
Detect and redact PII locally with SOTA performance
Real-time behavioral intelligence for call centers. Transcribes support calls, redacts PII, extracts emotional tone, classifies issues, and delivers insight-rich dashboards — powered by GPT-3.5 (cheap tokens), Whisper, DuckDB, and a polished React+TypeScript frontend. No Azure. No Power BI. No vendor lock-in. Just full-stack AI that runs local.
Logging Redactor is a Python library designed to redact sensitive data in logs based on regex patterns and / or dictionary keys.
Middleware library for pydantic-ai agents - before/after hooks for guardrails, logging, rate limiting, PII redaction, content moderation, and input validation.
Masker - PII Redaction API for LLMs. Remove personal data before sending to ChatGPT, Claude, etc.
🧠 Universal long-term memory for AI agents. GraphRAG-powered knowledge base with vector search + graph traversal. Privacy-first, local-only, MCP-compatible. Connect Claude, Copilot, or any AI assistant.
This repository contains a solution for Multimodal PII (Personally Identifiable Information) Redaction using Amazon Bedrock. The solution provides a workflow for detecting and redacting PII from emails and attachments using various AWS services including Amazon Bedrock Data Automation, Amazon Bedrock Guardrails, Lambda, S3, DynamoDB, and more.
🛡️ A privacy-first Chrome extension that intercepts clipboard data to redact PII (emails, keys, CCs) before pasting into AI assistants like ChatGPT & Gemini. 100% local, zero-leakage "privacy firewall."
DRAFT: This project synchronizes SysAid support tickets (Service Requests) into Azure DevOps (ADO) as Bugs
Lightweight PII redaction pipeline using Hugging Face NER + regex (Python) 96.5% accuracy
A secure, client-side PII masking tool that redacts sensitive information (emails, names, SSNs) locally in the browser before sending text to LLMs or GPT.
A Laravel package for scrubbing PII (Personally Identifiable Information) and sensitive data from Eloquent models. Useful for GDPR compliance and data retention policies.
⚡ REDACT V2 is a privacy-first desktop app that automatically detects and redacts PII (Personally Identifiable Information) from text, PDFs, and Word docs. Built with Electron.js & Node.js, it uses Hugging Face NER models for secure offline/online redaction with a clean UI.
Context hygiene & risk adjudication for LLM pipelines: secrets, PII, prompt-injection, policy redaction & tokenization.
Privacy first feature engineering pipeline transforming PII-rich customer data into analytics ready features without exposing personal identifiers.
A Cloud Native solution for detecting, alerting, and redacting PII (Personally Identifiable Information) from Kubernetes logs.
Structured audit logging agent for Sentinel proxy - compliance-focused logging with PII redaction
Add a description, image, and links to the pii-redaction topic page so that developers can more easily learn about it.
To associate your repository with the pii-redaction topic, visit your repo's landing page and select "manage topics."