Security & AI safety

Privacy tools

272 agents · most starred first

Privacy tools, page 3 of 3

llmshield

Shields your confidential data from third-party LLM providers.

llmshield-spanish-corpus

Spanish language corpus for LLMShield entity detection.

magento-encryptor
mask-llm

Privacy-safe LLM data cleaning for fine-tuning datasets

mask4llm

A terminal user interface (TUI) app built with Textual to easily mask and unmask sensitive information.

maskllm-py

Python SDK for MaskLLM

moat-lib-diffiehellman

A Pythonic implementation of the Diffie-Hellman key exchange protocol

myrage

A simple class to instanciate a tor process and run http requests behind it

ocultar-claude-mcp

Zero-egress PII protection for Claude AI workflows via MCP stdio

ocultar-mistral-mcp

Zero-egress PII protection for Mistral Le Chat workflows via MCP stdio

openai-agents-privacy-filter

PII redaction guardrails for OpenAI Agents SDK

openai-agents-tonic-textual

Tonic Textual PII redaction tools and guardrails for the OpenAI Agents SDK

openpgpcard-x25519-agent

Socket interface to Curve25519 ECDH from an OpenPGP card.

pebblo-langchain

Pebblo Gen-AI Data Analyzer

pii-masker-gpt

A hybrid PII detection, masking, and unmasking library using spaCy and regex.

pii-shield-llm

Safe LLM usage by automatically masking PII/PFI before it leaves your system.

piigpt

Provides a mechanism to anonymize PII and PHI before sending to a LLM API

pixelpin-auth-storage-sqlalchemy

Python Social Authentication, SQLAlchemy storage.

presidio-haystack

Haystack integration for Microsoft Presidio — PII detection and anonymization

proton-vpn-local-agent

Local agent library

py-diffie-hellman

Python implementation of the Diffie-Hellman key exchange protocol

pyrage
pyrage-stubs

A PEP 561 stub package for pyrage's types

secure-file-storage-milosz275

Secure File Storage is a secure, encrypted file storage solution developed in Python. It combines strong encryption, modular architecture, logging and basic access control.

sharag256

SHARAG-256: A patented cryptographic hashing algorithm combining SHA-256 compression rounds with complex mathematical randomization using trigonometric, exponential, and factorial functions. Patent-protected, production-ready, and designed for blockchain, federated learning, and distributed systems.

sofastorage

Easy to use password manager

swarmauri_mre_crypto_ecdh_es_kw

ECDH-ES+A128KW based multi-recipient encryption provider for Swarmauri

swarmauri_mre_crypto_keyring

Keyring-backed multi-recipient encryption provider for Swarmauri

swarmauri_mre_crypto_pgp

OpenPGP sealed-per-recipient MRE provider for Swarmauri

swarmauri_mre_crypto_shamir

Shamir secret sharing based MRE crypto provider for Swarmauri

szn-iptv-rus-gdpr-agent

Security placeholder package

tectonic-bedrock-python

Python bindings for the Bedrock cryptographic library

tenet-langchain

Tenet PII governance integration for LangChain agents

textual-haystack

Haystack integration for Tonic Textual PII detection, transformation, and entity extraction

ultrasonic-agentics

Steganography framework for ultrasonic agentic command transmission

agentforge-guard-presidio

Microsoft Presidio PII detector for AgentForge guardrails

vaultaire

Vaultaire review: compare features, pricing, use cases, access model, and alternatives for this Mobile App Builders agent in 2026. A private, end-to-end encrypted photo vault for iPhone

federated-agent-audit

Privacy-preserving audit framework for multi-agent AI systems. Detects cross-agent data leaks, inference attacks, and compliance violations — without accessing raw content.

@redactpii/node

Zero dependencies, blazing fast regex-based PII redaction with optional compliance dashboard integration. The modern fork of the abandoned 786k-download library.

pp-phragmen

Privacy-Preserving Phragmén Voting via Secure Multi-Party Computation

@opena2a/aicomply

Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI.

fingerprint-coherence

Browser fingerprint consistency checker — UA, Client Hints, WebGL, timezone lint. CLI: fp-coherence.

datamask-llm

DataMask LLM 推理引擎 — BERT-NER ONNX 推理、Deepseek 客户端、标注种子管理

@chatpanel/gateway

Local privacy gateway — redacts PII out of OpenAI/Anthropic API traffic before it reaches a model, then restores it in the reply. Point opencode, codex, aider, Claude Code, etc. at it.

cohere-tng

Python SDK for TNG — direct OHTTP encryption for confidential AI

ragleakguard

Scan your AI's vector database for exposed sensitive data.

sct-langchain

LangChain/LangGraph integration for SCT (Secure Compact Tokenization) — reversible, keyed PII pseudonymization (DSGVO/BaFin-grade) plus deterministic tool-output compression and a metered OpenAI-compatible chat model.

agentleak

Privacy-leakage testing for AI agents: audit the whole execution trace, score it deterministically, gate it in CI.

langchain-sct

Reversible PII pseudonymization + token compression for LangChain 1.0 — a keyed, DSGVO/BaFin-grade superset of the built-in PIIMiddleware.

llm-redact-proxy

Transparent local proxy that redacts private information from LLM requests and seamlessly restores it in responses

llm-shield-proxy

Streaming privacy gateway for configurable PII transformation and OpenAI-compatible proxy traffic.

promptshield-llm

Redact sensitive data from LLM prompts before sending them to a model.

ragkit-promptkit

A prompt template engine for LLM apps: validated variables, reusable few-shot blocks, and clean chat/message construction.

toolmask-llm

Mask PII in LLM tool-call outputs before they reach the model, with role-based access control. Zero dependencies.

veil-llm

Local DLP reverse proxy for LLM traffic

privrag-guard

Privacy-preserving middleware for embedding pipelines and vector search.

llm-sanitizer-gateway

Local AI traffic privacy gateway — mask sensitive data before it leaves your machine

llmveil

Reversible PII redaction for LLM pipelines. Local, deterministic, no network calls.

maskflow-litellm

MaskFlow guardrail for LiteLLM: mask PII (Indian IDs included) before a request reaches the provider, restore it in the response -- streaming and tool calls included.

maskflow-langchain

MaskFlow for LangChain: a reversible PII anonymizer/deanonymizer pair (drop-in for langchain-experimental's Presidio anonymizer) plus a leak-guard callback. Indian identifiers included.

maskflow-llamaindex

MaskFlow for LlamaIndex: a PII node postprocessor (drop-in for PIINodePostprocessor), an ingestion transform that keeps PII out of the vector store, and a reversible query engine wrapper. Indian identifiers included.

llmfy-guardrails

Standalone PII detection and masking guardrails for text pipelines (PIIGuard).

privllm

A reversible redaction layer for any LLM connection

shield-storage

Reserved name. The real 'shield-storage' is a private BlackShield package and is not distributed on PyPI.

stegstr-agent-tools

A Python wrapper for Stegstr CLI, allowing AI agents to easily hide and transfer secret data in images.

srift-transfer

Decentralized, end-to-end encrypted P2P file transfer, chat and calls: human to human, human to AI agent, and AI agent to AI agent. Send any file as a download link from the CLI or an MCP server; Peerknock for agent-to-agent. No account, no database.

claude-sonar

Local privacy and proxy consistency audit for Claude Code and agent skills

maskflow-agent

MaskFlow guard for AI coding agents (Claude Code, GitHub Copilot, Cursor, Codex, Antigravity, Gemini CLI, OpenCode, Cline, Devin Desktop): masks PII (Aadhaar, PAN, UPI, mobile, ...) in tool output before the model sees it, and restores values only inside allowlisted commands at run time.

zscams-agent

Async TLS tunnel client with SNI routing, auto-reconnect, and health checks (Python 3.7 legacy)

claude-ipcheck

Evidence-based Claude AI IP risk, proxy, DNS and timezone diagnostics

@fairquery/agent-trust-mcp

Fairquery Agent Trust & Data Safety MCP server: PII/secret redaction, email validation, sanctions screening, dependency checks and a local MCP server pre-check for AI agents. Free local tools + optional paid Apify-backed deep tools.

PII Blackout

PII Blackout is offline document redaction software. It permanently redacts names, IDs, emails, phones and other PII from PDF, Word and Excel on the device with Presidio + GLiNER; files never leave the computer.

More in Security & AI safety