Integration Guide

Stop Feeding ChatGPT Your Source Code

Every code snippet you share with ChatGPT trains OpenAI models and exposes your IP. Pretense routes your API calls through a local mutation proxy.

under 10msadded latency

Local-firstnothing leaves your machine

5 minsetup time

Byte-exactreversal guaranteed

How to Protect ChatGPT in 3 Steps

One environment variable. No code changes. No workflow disruption.

npm install -g pretense && pretense start. Proxy runs on localhost:9339.

Set OPENAI_BASE_URL=http://localhost:9339. All OpenAI SDK calls route through Pretense.

ChatGPT receives synthetic identifiers. Pretense reverses them in the response.

Pretense transforms your real identifiers into synthetic tokens before transmission. The LLM sees structure and logic, not your proprietary names.

Without Pretense: raw identifiers exposed

// Before Pretense mutation
async function getUserPaymentToken(userId: string) {
  return await stripeClient.createToken(userId, STRIPE_SECRET);
}

Your function names, secrets, and architecture are transmitted verbatim.

With Pretense: synthetic identifiers only

// After Pretense mutation (what the LLM sees)
async function _fn4a2b(_v8c3d: string) {
  return await _v2f1a._fn9e4b(_v8c3d, _v7d2c);
}

Structure intact. LLM quality preserved. Your IP stays private.

After the LLM responds, Pretense reverses every mutation. You receive real, working code with your original identifiers restored byte-for-byte.

terminal

$ OPENAI_BASE_URL=http://localhost:9339 your-app

$ pretense init

$ pretense start

NOTE

Set OPENAI_BASE_URL=http://localhost:9339 in your environment

Does this protect against ChatGPT model training?

Pretense mutates identifiers so ChatGPT never sees real function or variable names. Training data contains only synthetic names.

Does it work with the OpenAI API v1?

Yes. Pretense is OpenAI-API-compatible and supports all v1 endpoints including chat completions and embeddings.

What about the ChatGPT web interface?

The web interface does not use the API. For web chat, use our browser extension (coming soon).

No code changes. No workflow disruption. One environment variable and Pretense intercepts every request.

No credit card required. 30-second setup. Local-first, nothing leaves your machine.