BiVelio ShieldKeep sensitive data out of external AI models.
Keeps personal data and secrets out of ChatGPT, Claude and any other AI — caught and swapped before they ever leave your device or your servers. A free browser extension for people; a self-hosted gateway for developers and teams.
Available on Chrome, Edge & Brave · Firefox & Safari coming
Works with ChatGPT (OpenAI) & Claude (Anthropic)For everyone · Browser extension
Prefer zero setup? Get BiVelio Shield for your browser.
No code, no server, no account. Install the free extension and your sensitive data is redacted right on your machine — before it ever reaches ChatGPT or Claude.
Install it
Add BiVelio Shield to Chrome, Edge or Brave in one click. Nothing to configure.
Use AI as usual
Open ChatGPT or Claude and write normally — the extension runs quietly in the background.
Stay private
Emails, cards, IBANs, ID documents and secrets are redacted on your device before anything is sent, then restored in the reply.
Free · 100% local · No account
Add to ChromeFor teams · Self-hosted gateway
A fail-closed frontier in front of any AI API.
The self-hosted gateway (BV-PRGA) deploys on your own infrastructure and applies the same protection to all your AI traffic: sensitive data is reversibly pseudonymized, secrets are blocked, and if anything fails, the request does NOT leave.
pip install bivelio-privacy-gateway
Frequently asked questions about Privacy
The essentials about BiVelio Shield and the self-hosted gateway.
Is the extension really free?
Yes. BiVelio Shield for the browser is a free extension, 100% local and account-free. It installs in Chrome, Edge or Brave with one click; Firefox and Safari are coming soon.
Does my data reach BiVelio or the AI provider?
No. Detection and substitution happen on your own device (the extension) or on your own infrastructure (the gateway) before anything leaves. BiVelio never sees your data: sensitive values are replaced with placeholders before they reach ChatGPT, Claude or any other AI.
What's the difference between the extension and the gateway?
The extension is for individuals: zero configuration, it protects what you type into ChatGPT or Claude. The self-hosted gateway (BV-PRGA) is for teams and developers: it's deployed on your infrastructure and applies the same protection to all the AI traffic from your applications, via API.
What happens if a secret or an API key appears?
Personal data (names, DNI, IBAN, emails) is pseudonymized reversibly; secrets such as API keys are blocked outright. If something can't be protected, the policy is fail-closed: the request does NOT leave (a DENY decision).
Do I get the original text back in the response?
Yes. Pseudonymization is reversible: the placeholders are restored in the model's response, so you see the result with the real values even though the model never received them.
Which AIs and browsers does it work with?
Compatible with ChatGPT (OpenAI) and Claude (Anthropic), and with more models through the gateway. The extension works in Chrome, Edge and Brave today.