BiVelio ShieldYour data never reaches the model.
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)In plain words
What does BiVelio Shield actually do?
Four ideas, four short animations. This is the whole product.
You type as usual
Open ChatGPT or Claude and write the way you always do — with your email, your ID number, your IBAN or your card if you need to. Nothing about how you work changes.
It's redacted on your own device
Before a single byte leaves your browser, BiVelio Shield spots those sensitive values and swaps them for anonymous tokens. It all happens on your machine, not on a server.
The AI only ever sees tokens
The AI provider receives the tokens instead of your real data — never the email, the number or the document. What's yours stays with you.
You see your real data
When the reply comes back, the extension restores your real values on screen. The conversation reads normally; the trail left in the cloud stays anonymized.
The animations illustrate the idea. The technical detail — and the proof — is further down.
Why this matters
Most AI data leaks are not attacks. They are a paste.
A support ticket, a contract, a spreadsheet of customers, an API key in a stack trace. Pasted into ChatGPT or Claude on a busy afternoon, it becomes a disclosure to a third-party provider under that provider's terms.
What is never sent needs no paperwork
Personal data that stays on your machine needs no processing agreement, no transfer assessment and no breach notification. Redaction before the request is the simplest control there is.
Secrets are incidents, not personal data
An API key or a private key that reaches a model is compromised the moment it leaves. BiVelio blocks those sends outright and tells you which key it was.
The AI still works
Tokens keep the structure of your text, so the model can reason about a customer, an IBAN or an email without ever seeing the real value. The reply is restored on your screen.
How it works
Redact before the request, restore after the reply.
The same pattern in both products. The provider only ever receives placeholder tokens; the real values never cross the line.
Round trip, protected in flight
Detected values travel as placeholders; the response comes back with the values restored on your device.
What leaves
[BV:PERSON:a1b2c3] · [BV:IBAN:2e5d8c] · [BV:EMAIL:5fe7e6]
What you see
María García · ES91 2100 0418… · maria@acme.com
Add BiVelio Shield to Chrome, Edge or Brave in one click. Nothing to configure.
Open ChatGPT or Claude and write normally — the extension runs quietly in the background.
Emails, cards, IBANs, IDs and secrets are auto-redacted, then restored in the reply. Redaction runs on your machine, before your prompt is sent.
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.
- Free
- 100% local
- No account
Firefox & Safari comingWho it is for
One engine, three ways to use it.
Pick the one that matches how you work. All three run the same checksum-validated detection and the same fail-closed rules.
Lawyers, doctors, accountants, consultants
You work with other people's data every day and you want to use AI without becoming the weak link. Install the free extension and keep working exactly as before.
Get the free extension →Compliance without a rollout project
Give every seat the same protection, add attachment redaction for PDF, Word and Excel, and see value-free counts of what was kept out of the cloud in the dashboard.
See team pricing →A DLP layer between your code and any LLM
Run the self-hosted gateway inside your perimeter and point your OpenAI or Anthropic SDK at it. One line of configuration, four endpoints covered, everything else denied.
Read the developer track →See the full comparison
Same detection engine everywhere. The difference is where it runs and what it can reach.
| Shield · Free | Shield · Pro | Gateway · Self-hosted | |
|---|---|---|---|
| Where redaction runs | Your browser | Your browser | Your infrastructure |
| Works with | ChatGPT, Claude (web) | ChatGPT, Claude (web) | Any OpenAI / Anthropic SDK |
| Structured identifiers — IBAN, cards, IDs, emails, phones, IPs | Yes | Yes | Yes |
| API keys & secrets blocked outright | Yes | Yes | Yes |
| GDPR Art. 9 special-category lexicon | Yes | Yes | Yes |
| Attachments — PDF, Word, Excel, PowerPoint, text | No | Yes | Yes |
| Names, addresses, free text (NLP layer) | No | Optional, off by default | Local models |
| Custom dictionaries — codenames, clients, projects | No | No | Yes |
| Dashboard with value-free counts | No | Yes | Yes |
| Account required | No | Licence | Licence |
| What reaches BiVelio | Nothing | Seat check-in (no content) | Value-free counts (optional) |
| Price | Free | €4 / seat / mo + VAT | €4 / seat / mo + VAT |
Pro and the gateway share one subscription: a seat is a machine or a service identity, and the same licence token works in both.
Try it live
See it redact — and put it back.
Paste a support ticket, a code snippet, a customer record. Watch sensitive values get pseudonymised or redacted before they'd reach the model, then restored on the way back — all in your browser. Nothing you type leaves this page.
195 / 20,000
Hola, soy Marta y necesito ayuda con mi cuenta. Mi correo es [BV:EMAIL:ee14950f10] y mi teléfono [BV:PHONE_ES:27278110ce]. Adjunto mi DNI [BV:SPANISH_DNI:3524006bcd] y el IBAN [BV:IBAN:9629b822e9] para la verificación.
Hola, soy Marta y necesito ayuda con mi cuenta. Mi correo es marta.ruiz@empresa.es y mi teléfono +34 612 345 678. Adjunto mi DNI 12345678Z y el IBAN ES9121000418450200051332 para la verificación.
This runs the gateway's deterministic layer (checksum-gated IDs, IBAN mod-97, Luhn, secrets) ported to your browser — the same algorithms the server runs, with 0 values leaving your device. Names & free-text PII are the licensed NLP layer, not shown here.
Measured, not claimed
We don't ask you to trust us — we prove it.
And we're just as clear about what we don't do: names and free-form text are handled by the optional AI layer — right almost always, but its measured combined leak is 4.875%, not zero.
What it catches
Strong on the data that has a shape.
Structured identifiers are checksum-validated, so false positives stay near zero. Secrets are treated as incidents, not personal data.
Structured identifiers
DNI/NIE/NIF/CIF, IBAN (mod-97), cards (Luhn), ES/AD phones, email, IPv4 — every match validated by its checksum, then reversibly tokenised so the value round-trips: zero data loss.
Secrets & keys
OpenAI/Anthropic/AWS/GCP/GitHub/Stripe keys, JWT (header-verified), PEM private keys, connection strings. Detected → blocked → treated as compromised.
Names & places (NLP)
Multilingual NER (Presidio + spaCy, ensembled with GLiNER) for people and locations that have no structural signature — es · ca · fr · en · pt · de tuned, ~100 more languages via GLiNER.
Tenant dictionaries
Codenames, unannounced clients, internal labels — the confidential data no generic model knows about, declared per tenant.
For developers & teams
The gateway & SDK
Self-hosted, fail-closed DLP between your services and any LLM. Point your OpenAI/Anthropic SDK at it — nothing sensitive reaches the provider.
Try it in 30 seconds
Two commands in your terminal and you see it: sensitive data goes in, replaced data comes out. The same command then works in your scripts and CI.
$ pip install bivelio-privacy-gateway
$ echo "IBAN ES91 2100 0418 4502 0005 1332" | bpg scan
IBAN [BV:IBAN:49993624f2]One line to integrate
Your AI traffic goes through your own gateway, in your infrastructure: it replaces sensitive values before forwarding each request to the provider and returns them restored in the response. For your code it is one line: the address.
client = OpenAI(
base_url="https://bpg.internal/v1",
)If anything fails, the request does not leaveDENY
Pricing
One price. Your data stays yours.
The deterministic core is free and self-hosted, forever. Pro adds the NLP layer — see it live in the Playground, then subscribe to run it in your app. Per seat, in EUR.
Billed per seat. Or €39 / seat / yr (save ~19%).
A seat is an active machine or service identity, not a person — billed per seat on your subscription.
Prices exclude VAT. BiVelio Shield is business software: a valid EU VAT number is required at checkout, and the reverse charge applies.
Get started →- Every detector + the NLP contextual-PII layer
- 122 GDPR data types + 14 Art. 9 special categories
- Audit dashboards and signed managed rule bundles you install
- Attachment redaction: PDF, Word, Excel & text files rewritten locally before they upload
- Self-hosted: your prompts never leave your infrastructure
Questions
Frequently asked
Does my text leave my computer?
With the extension, your prompt is redacted inside your browser before the request is sent. The AI provider you chose receives the tokenised version; BiVelio receives nothing. With the gateway, the same happens inside your own infrastructure.
Can the AI still help me if it only sees tokens?
Yes. A token such as [BV:IBAN:2e5d8c] keeps the type and the position of the value, so the model can reason about it exactly as it would about a real one. When the reply comes back, the real value is restored on your screen.
What does it not catch?
The free tier does not remove people's names, postal addresses or free-form text: those have no fixed pattern and belong to the optional NLP layer. It does not protect voice or realtime modes, it does not cover Claude's Cowork composer, and on the free tier attachments are uploaded as-is with a notice. All of this is written in the extension's privacy policy.
How is this different from the provider's own privacy settings?
Opting out of training does not stop the provider from receiving, processing and retaining your data under its terms. BiVelio changes what is sent in the first place, so there is nothing to opt out of.
Does it help with GDPR compliance?
It applies data minimisation before the data reaches a processor: what was never disclosed needs no processing agreement, no transfer assessment and no breach notification. It is a technical measure, not legal advice; your obligations for the data you do send are unchanged.
What happens if detection cannot run?
The send is stopped and the popup tells you that protection was interrupted. Fail-closed means a doubt is resolved by not sending, never by letting the text through.
Extension or gateway?
The extension is for people using ChatGPT or Claude in a browser: install and forget. The gateway is for software: your services point their OpenAI or Anthropic SDK at it and every request is inspected in place. Teams often use both.
Can I verify the published figures?
Yes. The benchmark that produces them ships with the gateway (make benchmark), and the Playground on this page runs the same engine in your browser so you can test your own text without it leaving the page.
Where are BiVelio's own servers?
The website and its functions run in Frankfurt, the account database in Frankfurt, and the Sandbox in Germany. Stripe handles payments and Resend delivers invitation emails, both from the United States, and Google receives consent-gated ads measurement from the public pages only. The service privacy policy names all three rather than hide them under a general EU claim.
Does the gateway phone home?
No. The licence is a signed entitlement verified offline against BiVelio's public key. Value-free usage counts can be reported to the dashboard if you configure it, and never include prompt text or detected values.
Ready when you are
Ready to use AI privately?
Install the free browser extension in one click, or set up the self-hosted gateway for your app or team.