vissnia/piast-gate
Open-source gateway for anonymizing sensitive data before sending to LLM APIs
This tool helps businesses and individuals use Large Language Models (LLMs) without exposing sensitive personal information. It takes your original text containing data like names, emails, or national identification numbers, replaces them with placeholders before sending to an LLM, and then restores the original data in the LLM's response. It's designed for anyone who needs to process Polish language text with LLMs while ensuring data privacy.
Use this if you are processing Polish text with Google Gemini and need to ensure that Personally Identifiable Information (PII) is never directly exposed to the LLM API.
Not ideal if you need to work with LLMs other than Google Gemini or with languages other than Polish, as it currently only supports these.
Stars
7
Forks
1
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/vissnia/piast-gate"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cxumol/promptmask
Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless...
sgasser/pasteguard
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.
AgenticA5/A5-PII-Anonymizer
Desktop App with Built-In LLM for Removing Personal Identifiable Information in Documents
rpgeeganage/pII-guard
🛡️ PII Guard is an LLM-powered tool that detects and manages Personally Identifiable Information...
subodhkc/llmverify-npm
AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency,...