dfki-dsa/pii-guardrail-browser-extension

PISIGuard runs entirely in your browser. It spots names, email addresses, phone numbers, credit card numbers, passwords, API keys, and more, replaces them with safe placeholders, then puts the real values back into the AI’s reply. From your point of view, it’s mostly invisible; from the AI’s point of view, the sensitive stuff was never there.

Swap the personal details out of your AI prompts before they are sent. On-device detection, no server, no account.

AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding agents.

DataCloak is a local-first sensitive-data protection layer for AI prompts.

Privacy proxy for your OpenAI requests

Local-first tool that strips emails, secrets, paths, and other identifying content out of your prompts before they reach a cloud LLM — and rehydrates the response locally.

Prevent accidental PII leakage in LLM prompts before they hit the model.

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.