Query Sanitizer

1

Redacts sensitive data from prompts using a local model before they reach external LLMs, with automatic restoration in responses.

GitHub
Category Models
Language Python
Added Mar 28, 2026
Views 55

About

DLP middleware that intercepts prompts, runs them through a local model (Ollama or LM Studio) to replace sensitive tokens like employee names, project codenames, infrastructure details, and credentials with typed placeholders. Maintains a ledger for automatic restoration in responses. Supports configurable organization-specific detection rules and categorizes findings by severity.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/query-sanitizer.svg)](https://hifriendbot.com/ai-list/query-sanitizer/)
Listed on AiList

Compare

Query Sanitizer vs Prompt Cleaner Query Sanitizer vs GitHub with MCP Armor Query Sanitizer vs PII Anonymizer

Similar Projects

Prompt Cleaner

1

Sanitizes and redacts sensitive information from user prompts using OpenAI-compatible APIs to intelligently clean text while detecting and removing API keys, tokens, emails, and other secrets before processing.

APIs

GitHub with MCP Armor

Read-only GitHub integration with security filter layer that scans responses for 95+ secret patterns and redacts them before reaching AI.

MCP Servers

PII Anonymizer

Detects and redacts personally identifiable information before processing sensitive text, all locally.

MCP Servers

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project