pii-masking

Admin-approved, audited SQL gateway — Slack + web IDE, tier-matched creds (RO/RW/DDL), PII masking, full audit. PostgreSQL & SQL Server.

🛡️ Programmable Guardrails for LLM Applications in Java. A framework-agnostic toolkit for input/output validation, PII masking, and jailbreak detection. The Java alternative to NVIDIA NeMo Guardrails.

A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

Zero-Latency PII Scrubbing Middleware Agent for Enterprise Cloud Compliance.

Anonimizador de dados pessoais (PII) em textos em portugues brasileiro.

Protect personal data (PII) in your LLM prompts. piighost hides sensitive values from the model, then restores the real values in the response, so tools and the user still get the real data. Pluggable detectors (regex, NER, LLM), LangChain, Pydantic and LlamaIndex AI integrations, and a companion OpenAI/Anthropic proxy.

Your data, explored locally — and your AI agents kept on a leash. A federated data explorer with governed agentic access.

The sensitive data firewall for AI. Detect and mask PII (Emails, Credit Cards, CPFs) locally with zero-latency before sending prompts to LLMs. Thread-safe & Production ready.

Reversible PII tokenization for LLM prompts and web pages. Names, IBANs, Phone numbers, cards and secrets leave as tokens, and the mapping back to the real value never leaves your infrastructure.

A unified data masking library for Spring Boot applications that consistently masks sensitive data in JSON responses and logs, reducing GDPR/DSGVO risks while enabling secure audit and security logging.

Chat with AI. Keep Data Private. The AI Privacy Firewall. Anonymize ChatGPT, Claude, Gemini & Grok prompts — local PII masking for names, emails, phones, IBANs, credit ▎ cards, API keys, JWTs (30+ types). Shadow DOM secure overlay. GDPR & data sovereignty. Chrome + Firefox.

Turn any database into an MCP server - visually

An OpenAI-compatible reverse proxy you run yourself. It gives you the features of an AI gateway (guardrails, budgets, rate limits, multi-provider routing) but under your control from your client.

A library and SDK to redact sensitive content from GenAI/LLM telemetry (prompts, completions, tool arguments) before it reaches observability backends. Supports OpenTelemetry conventions.

Metadata-Driven Data Masking Engine for Salesforce (Sandbox Compliance)

On-prem detection & anonymization of PII and sensitive data for LLM inputs — hybrid regex + NER + local LLM

Self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, offline-verifiable Ed25519 receipts per access when a receipt sink is configured, coverage reconciliation against the DB's own query counters to surface gateway bypasses, and conformance vectors. MCP-native. MIT.

Open-source macOS clipboard history manager with built-in PII scrubbing. Detects and masks emails, API keys, credit cards, SSNs, and 35+ patterns locally. Free, local-only, no cloud.

Local-first PII redaction for Prime Agent: every request leaving your machine is rewritten to stable, typed placeholders by a deterministic recognizer plus an on-device ONNX classifier. Placeholders stay coherent across sessions and persisted harness data, and raw PII is never written to disk.

Transport-layer data masking for deepseek-harness (dsh): the model sees placeholders, you see real values restored live in the stream.