Security & AI safety

Privacy tools

272 agents · most starred first

Privacy tools, page 2 of 3

llm-redact★ 8

Large Language Model (LLM) information redactor that prevents private information from being sent to LLMs from agentic tools by substituting placeholders for private information on outgoing requests and then replaces the placeholders on the incoming responses seamlessly for the agentic tool users.

secret-guard★ 8

LLM Gateway to Protect your Secrets — redacts secrets before they reach LLM providers, restores them locally

OpenObscure★ 7

On-device privacy firewall for AI agents — encrypts PII with FF1 FPE before it reaches the LLM, scans responses for manipulation.

hexlock★ 7

PII redaction that preserves data format, tokenized values stay usable in LLM pipelines

Tabayyan★ 7

Saudi-aware PII detection & redaction for LLM pipelines. Checksum-validates National ID, Iqama, IBAN, CR, VAT, +966 numbers, passport & more; evasion-resistant; redacts before OpenAI/Anthropic with PDPL/NDMO audit. Local-first, zero telemetry.

genpark-pedersen-vector-commitment-homomorphic-skill★ 7

Information-theoretically hiding and computationally binding Pedersen vector commitments with additive homomorphic properties over prime fields.

genpark-agentic-zero-knowledge-pii-token-vault-masker-skill★ 7

Enterprise Zero-Knowledge PII Tokenization Vault & Prompt Masker. Reversibly anonymizes social security numbers, credit cards, passport numbers, email addresses, and phone numbers before sending prompts to external LLMs, restoring original | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550

veilstream★ 6

Streaming PII proxy for LLM chat. Pluggable detector, per-session vault, and cryptographic provenance-anchored reversal (PASP) that closes the false-attribution attack every other streaming library silently has.

soulprint★ 5

🔐 Decentralized KYC for AI agents — ZK proof of human identity behind any bot. No servers, no companies, no PII stored.

prompt-sentinel★ 5

Python library designed to protect sensitive data when interacting with third-party LLMs.

Emotion-Cipher-System★ 5

A secure emotion-aware text processing system that combines RSA encryption with AI-powered emotion analysis.

masker★ 5

Masker - PII Redaction API for LLMs. Remove personal data before sending to ChatGPT, Claude, etc.

veil★ 5

🔐 End-to-end encryption for LLM inference. The Signal protocol, applied to AI. Your prompts stay private.

OpenAI-GPT-Powered-Behavioral-Biometrics★ 5

Behavioral biometrics is a cutting-edge field that focuses on analyzing user behavior to enhance security and authentication processes. This repository serves as a hub for everything related to this innovative technology. Read more at 👇👇👇

redactum★ 5

⛨ redactum — automated PII & secret redaction for AI, APIs, and developer tools. Protects prompts, logs, and payloads before they leave your system. Lightweight and TypeScript-first.

sd-jwt-dotnet★ 5

Selective Disclosure for JWTs (SD-JWT) .Net implement

LocalGuard★ 5

Transparent HTTP proxy that redacts secrets and PII before they reach LLM providers. Works with OpenAI, Anthropic, Gemini, and 25+ providers.

federated-agent-audit★ 5

Privacy audit for multi-agent AI systems (CrewAI · LangGraph · AutoGen) — detect compositional data leaks without the central auditor ever seeing raw content.

exodus-ia-firewall★ 5

🛡️ Local privacy firewall for AI coding agents — masks API keys & personal data before they reach the cloud, then restores them transparently.

lokalite★ 5

Local-first secrets manager for macOS. Encrypted vault, menu bar app, CLI, and an MCP server that loads secrets into your coding agent's shell instead of the chat. No cloud, no account, no subscription.

EnigmAgent★ 5

EnigmAgent — 6-layer encrypted vault for AI agents (AES-256 + ChaCha20 + Blowfish + Fernet + 3DES + RSA). P2P sync via Gun.js. Zero cloud. Part of P2PCLAW.

confession-chain★ 5

Package pseudonymous confessions with local redaction and permanence warnings.

PrivacyFlow★ 5

PrivacyFlow: Keep secrets local. Keep agents working.

dead-drop-sol★ 5

Prepare encrypted-message metadata and recipient hints without exposing plaintext.

mcp-152fz-anonymizer★ 5

Автоматическое обезличивание персональных данных (ПД) по 152-ФЗ. Готовый MCP-сервер и API для безопасной работы ИИ-агентов, n8n и LLM.

hamza★ 5

An egress gate for CLI coding agents. Masks secrets and customer data in the request body before it reaches the model provider, and the agent keeps working.

cross-border-network-best-practices★ 5

AI Agent Skills for cross-border networking and censorship circumvention, made for ordinary users — install, harden, configure, and troubleshoot tools like 3X-UI / Xray.

forgd-verdict★ 5

Data loss prevention for Claude: finds secrets and personal data in prompts and responses, blocks prompts through inference hooks, and scans Compliance API history. Self-hosted on Azure, AWS or Google Cloud.

dina★ 4

An open-source protocol for sovereign personal AI - cryptographic identity, encrypted vaults, peer-to-peer messaging, and a trust network which prioritises privacy and truth over ads and marketing. MIT licensed.

agent-middleware-for-order-management-agent★ 4

Implemented enterprise AI agent middleware using Microsoft Agent Framework — authentication, PII redaction, and tool validation as middleware layers around an Order Return Management agent.

team2-SafeSurf★ 4

Safesurf - Dein Chat-Buddy um deine Internetsicherheit zu checken und zu verbessern!

openvpn-profile-validator★ 4

When you have a batch of OpenVPN profile files, but some of them may have connection issues, this program can help you verify them in bulk and quickly identify the available profile files. It is usually used for quick verification of manual OpenVPN configuration files provided by Surfshark.

NotNet★ 4

NotNet is a project aimed at raising awareness about the poor state of the internet in Iran.

manage-access-control-in-generative-ai-powered-search-applications★ 4

Manage access control in RAG applications for enterprise customers

armos-python★ 4

Open source PII masking middleware for OpenAI and Anthropic SDKs

PII_Compliance_Check_MCP★ 4

gradio mcp-server-track mcp-server region:us

Trustguard_AI★ 4

AI-powered privacy policy analyzer built for Microsoft's Agents League Hackathon 2026 (Reasoning Agents track). 6 specialized AI agents extract, reason, detect dark patterns, score readability, audit user rights, and benchmark policies against TikTok, Facebook & more — covering GDPR/CCPA/PDPA/PIPEDA/LGPD/DPDPA. Built with Flask + Microsoft Foundry.

Privacer★ 4

Detect and redact sensitive data in LLM requests — before they leave your machine.

onecipher★ 4

AI Native Security Tool for Wallet && Password management.

gaap★ 4

Welcome to GAAP (Guaranteed Accounting for Agent Privacy). This agent execution environment keeps your private data safe.

aanu-vault★ 4

Zero-knowledge personal vault — notes, passwords & files encrypted client-side (AES-256-GCM) before they ever touch the server. Next.js, Supabase, WebAuthn passkey unlock.

closemask★ 3

Privacy shield for AI Agents: Automatically mask PII and credentials before sending to LLM APIs. Supports tool calls & streaming.AI Agent 隐私防护盾:在调用 LLM API 前自动遮罩个人身份信息和凭据。支持工具调用与流式响应。

PrivacyCopilot★ 3

Local-first Rust/Tauri desktop AI assistant with encrypted storage, provider settings, image chat, artifacts, SQLite history, and vector search.

dlp_assistant★ 3

gradio region:us

pyveil★ 3

Local PII and secret redaction for Python LLM apps and AI agents. Zero dependencies. Prompts, tool calls, MCP, memory, logs, and traces.

Vault-Session★ 3

Export and import browser cookies securely using AES-GCM encryption for seamless session migration across devices without third-party servers.

flock-alpr-toolkit★ 3

Provide tools and redacted documents for community research and governance of automated license plate recognition systems with adaptable formats.

domestique-oss★ 3

A local AI firewall for developers — redacts secrets and PII from your prompts before they reach OpenAI, Anthropic, or any LLM. No CA, no system proxy, no admin.

awg-veil★ 2

VeilAWG — vendor-independent CLI client and Python library for AmneziaWG 2.0 with advanced traffic obfuscation. Docker-first and agentic-ready. MIT licensed.

data_redactor★ 2

A Ruby gem with a C extension for scanning and redacting sensitive patterns (AWS keys, Italian fiscal codes, passport numbers, etc.)

zhimi-browser★ 2

智密浏览器 Zhimi Browser — 基于 Chromium 源码级定制的国密(TLCP/SM2/SM3/SM4)+ 大模型 AI 浏览器。A GM-crypto (TLCP/SM2/SM3/SM4) + LLM browser built on Chromium.

mask★ 2

Enterprise-grade AI Data Loss Prevention (DLP) for LLM agents using Just-In-Time encryption and format-preserving tokenization.

ConsentFlow-Debugger★ 2

AI-agent ready (MCP): ask Claude or Cursor to check any live page for tags that fire before consent, even after clicking accept or reject, and get the fix. Also a Chrome extension and a CLI. Read-only.

data-anonymization-tool

Data Anonymization Tool review: compare features, pricing, use cases, access model, and alternatives for this Translation AI Agents agent in 2026. Safeguard Sensitive Information with Automated Redaction

tea-checker

Tea checker review: compare features, pricing, use cases, access model, and alternatives for this Authentication Agents agent in 2026. Discreet Tea app profile lookup with verified results in 24 hours.

Phala

Phala offers private AI models and compute you can truly trust.

DiffehellmanAlphaCalculator
SecretStorage

Python bindings to FreeDesktop.org Secret Service API

SecretStorage-Setup

Ease setup of SecretStorage in virtualenvs

agent-comply

Compliance middleware for AI agents. PII redaction, audit logging, consent management, and DPIA generation in 3 lines of code.

agent-data-residency-mcp

Agent data residency + GDPR Chapter V transfer-basis runtime guard. Programmatically answer 'where does this data live?' for agent-to-agent transfers. Adequacy decisions, SCCs, BCRs, EU AI Act Article 10.

agent-framework-purview

Microsoft Purview (Graph dataSecurityAndGovernance) integration for Microsoft Agent Framework.

agentfud-password-manager

AgentFUD Password Manager

anonLLM

Anonymizes personally identifiable information for Large Language Model APIs

auraagent

Aura — Carbon tracking and AI bias analysis toolkit

auragyt-sdk

AuraGyt Python SDK for biometric authentication and identity verification

azureaicommunity-agent-pii-middleware

PII detection and security middleware for AI agent pipelines

blindllm

A library for making anonymized calls to LLM APIs

claude-anonymizer

Drop-in redaction proxy for the Anthropic API — anonymize prompts, deanonymize responses, log the redacted form for compliance.

claude-code-scrubber

Scrub personal info, secrets, and API keys from Claude Code transcripts before publishing

cloakllm

AI Compliance Middleware -- PII protection, tamper-evident audit logs, and EU AI Act compliance for LLM gateways

contextual-privacy-llm

A toolkit for safeguarding contextual privacy in LLM prompts

diffiehellman

A Pythonic implementation of the Diffie-Hellman key exchange protocol

diffiehellmanlib

Diffie-Hellman key exchange library

dina-agent

CLI client for Dina Home Node — encrypted memory, PII scrubbing, action gating

discord-data-storage

Encrypted data storage with a format based on Discord

django-mirage-field

A Django model fields collection that encrypt your data when save to and decrypt when get from database. It keeps data always encrypted in database.

django-pzip-storage

Storage backend for Django that encrypts/compresses with PZip.

dragocrypt

For developers

dragon-e

Encrypt like a dragon: new method for securing data

encrypt-storage

Позволяет использовать Яндекс диск как хранилище с шифрованием

fhe-secure-agent

GPU-accelerated FHE security layer for any LLM agent — any NVIDIA GPU

generic-storage

Tools for extract sensitive configuration out of your project

gllm-privacy-binary
gpt-guard

A lightweight library to sanitize data provided to AI tools

kan-secret-storage

Python Secret Storage package

langchain-ambientmeta

LangChain integration for AmbientMeta Privacy Gateway — protect PII in LLM calls

langchain-blindfold

LangChain integration for Blindfold PII detection and protection

langchain-nopii-middleware

LangChain agent middleware that routes model calls through the NoPII PII-tokenization proxy

langchain-textual

LangChain integration for Tonic Textual PII redaction

llama-index-postprocessor-presidio

llama-index postprocessor presidio integration

llama-index-readers-pebblo

llama-index readers pebblo integration

llamaindex-ambientmeta

LlamaIndex integration for AmbientMeta Privacy Gateway — protect PII in LLM calls

llm-anon

CLI tool to anonymize code using local LLM before sending to Claude Code

llm-mask

Mask sensitive data in documents using a local OpenAI-compatible LLM

llm-privacy-filter

A lightweight LLM-based privacy filter for masking sensitive entities in text.

llm-redact

Privacy-first text redaction using local LLM models with rule generation capabilities

llm-redacted

A lightweight, zero-dependency output sanitizer for secrets, API keys, and PII.

llm-safe-pl

DEPRECATED — use pii-veil + pii-core instead. Reversible PII anonymization for Polish documents.

llm-securescan

A new package is designed to facilitate secure and structured user interactions with language models by analyzing and extracting specific information from user-provided text. It uses pattern matching

More in Security & AI safety