Like a call with no recorder
Your words reach the AI, it answers, and then they're gone. Nothing is saved to read back later, not by us, not by anyone.
Provable privacy
Don't trust us.
Check.
Everyone says “we don't keep your data.” Here's how you can actually tell the difference with RedBeard. In plain words first, then the full technical detail.
We never write your conversations down.
We only keep a tally
The one thing we count is how much you've used, so your plan's limits work. It's like a gym counting your visits without filming you.
You don't have to believe us
The code that runs RedBeard is out in the open, so anyone who can read code can confirm it never saves what you type.
What happens to your message.
Yousend a message
Gatewaychecks your key
The modelreads it, answers
Youget the reply
Usage counter +1the only thing written to disk
Your wordsheld in memory for that one moment, then gone. Never written down.
Everything we keep. The whole list.
Our database has exactly two tables. Neither one has a place to put your messages.
Keys
- a fingerprint of your key (not the key itself)
- your plan and how much you've used
- when your access runs out
Orders
- a payment reference and amount
- whether it's paid
- no name, no email, no address
Conversations
There is no such table. We have nowhere to put your prompts or the AI's replies. They never touch our disk.
How it actually works.
The path a request takes
Your request hits the gateway. It checks your key's fingerprint and remaining allowance (a read of the keys table), forwards your messages to the model, and streams the reply straight back to you. When the reply finishes, the only thing written back to the database is your updated usage counters. Your prompt and the model's answer live in memory for the length of that one request and are never persisted.
What's in the database, exactly
Two tables and nothing else: keys (key hash, plan, usage counters, paid-until, prepaid balance) and orders (order id, payment reference, amount, status). There is no column anywhere for message content. Our own test suite asserts this: it sends a conversation through, then checks that the text appears in no table.
How you verify it
A privacy policy is a promise. Source code is checkable. The gateway's full source is public on GitHub, so you can read these guarantees for yourself and confirm that no request body is ever written to storage.
The honest limit
For any AI to answer you, the computer running the model has to read your actual words. There is always a moment, during that one request, when your text is in the server's memory. What we control, and what we promise, is that it is never written down afterwards. Making it so even the operator can never see the plaintext needs confidential computing (a secure enclave with a cryptographic attestation). That's a real technique and a direction we're exploring, not something we claim today.
Why we don't just encrypt the logs
Because encrypting your conversations means we'd be keeping them, in a locked box, and holding the key. Storing nothing is strictly stronger than storing a locked box we can open. The goal isn't a better lock. It's having nothing to lock up.
Questions about any of this? It's all in the docs, and in the open source.