Integration Guide

Semantic Kernel + AI Privacy Gateway

Microsoft Semantic Kernel with enterprise-grade AI data protection

TL;DR: Semantic Kernel is Microsoft's AI orchestration framework. Route it through AI Privacy Gateway to add PII masking to all your AI plugins and planners..
Integration = one config change. No SDK changes needed.

Why Add PII Masking to Semantic Kernel?

Semantic Kernel is Microsoft's AI orchestration framework. Route it through AI Privacy Gateway to add PII masking to all your AI plugins and planners.

How It Works

Your App + Semantic Kernel
→
Privacy Gateway
(masks PII locally)
→
AI API
(receives clean data)
✓ PII masked before leaving your machine ✓ Zero code changes in your Semantic Kernel integration

Benefits

✓
Enterprise-grade data protection for .NET AI apps
✓
Works with Semantic Kernel planners, plugins, and functions
✓
Drop-in endpoint change — zero plugin code changes

Setup: Connect Semantic Kernel to AI Privacy Gateway

Configuration — Change One Line
// In your Semantic Kernel configuration
var kernel = Kernel.CreateBuilder()
    .AddOpenAIChatCompletion(
        modelId: "gpt-4o",
        endpoint: new Uri("http://localhost:9999/v1"),  // Privacy gateway
        apiKey: "your-api-key"
    )
    .Build();

Step-by-Step Setup

  1. 1 Deploy gateway: docker run -d -p 9999:9999 ghcr.io/gunxueqiu6/ai-privacy-gateway:lite
  2. 2 Configure your Semantic Kernel OpenAI/OpenAI-compatible endpoint to localhost:9999/v1
  3. 3 All plugin and planner prompts are now PII-masked

Start Protecting Your Semantic Kernel Data

Deploy AI Privacy Gateway in 30 seconds. Free and open source.

Get Started Free View Docs

Frequently Asked Questions

Does this work with the latest version of Semantic Kernel?

Yes. AI Privacy Gateway works at the HTTP layer as a transparent proxy. It is compatible with any version of Semantic Kernel that makes HTTP API calls.

Will this affect my Semantic Kernel performance?

The gateway adds less than 1ms per request. The PII detection engine is written in Rust for maximum throughput, so your Semantic Kernel application performance will not be noticeably affected.

Can I use this with multiple AI providers through Semantic Kernel?

Yes. Route all your AI API calls through the same gateway. It works transparently with any OpenAI-compatible API — just change the base URL.