Your clients’ names never reach the AI

Anonymise your AI conversations instantly

lexform sits in your browser and anonymises everything you write to Claude and ChatGPT. The AI never sees your data, and confidentiality is preserved.

Lawyers, accountants, HR, healthcare · processed in the EU · nothing is ever stored

claude.aiextension lexform active
Écrivez à Claude…
Works withClaudeChatGPT web versions, in Google Chrome

Sovereignty

Processed in the European Union. Nowhere else.

The one service you are trying to protect yourself from cannot be the one doing the protecting. So the substitution runs on our own model — an open-source model we adapted to professional documents and host ourselves, on OVH hardware in Gravelines, France 🇪🇺. No US provider anywhere in the chain, except the AI you are talking to — and it only ever receives pseudonymised data.

🇪🇺 Never leaves the EU : servers and processors at OVH, Gravelines, FranceOpen-source model : adapted in-house to professional and legal documentsSelf-hosted : no OpenAI, no Google, no third-party cloud in the chainNothing retained : processed in memory, never written to a disk

Your browser

The file, in the clear

What you type and what you attach stays identifiable here, on your machine, and nowhere else.

lexform · EU-hosted 🇪🇺

Substitution · OVH Gravelines

Detection and masking run in memory on our European servers, then everything is wiped. No trace, no copy.

ChatGPT, Claude…

Placeholders, and its job

The AI reads PERSON_1, COMPANY_1 and reasons just as well. It has never seen your clients.

Firewall for Claude & ChatGPT

Nothing changes in how you work, except the risk.

No portal to open, no copy-pasting, no extra tool to learn. You keep writing on claude.ai and chatgpt.com; the extension handles the rest, in the background.

1

Create your account

Thirty seconds, no card required. 8,000 credits free every month.

Create my account

2

Install the extension

From the Chrome Web Store, in one click.

Install the extension

3

Link it to your account

One key to copy from your account and paste into the extension. Once, and never again.

4

Get on with your work

The lexform badge confirms protection is on. After that you stop thinking about it.

How it works

The AI does the work. Without the names.

01

You ask your question

With the real file and the real names, exactly as you would brief a colleague.

02

Identifying details are replaced

People, companies, addresses, emails, bank details, references — each becomes a neutral placeholder: PERSON_1, COMPANY_2. Done on our own model, inside the EU.

03

The AI works on placeholders

It analyses, drafts and calculates without ever holding an identifying detail. Nothing you send can be used to train it.

04

You get the real text back

The mapping never left your machine. On your screen the real names come back; for the AI, they never existed.

Try it now

Drop a document. We handle the rest.

Traité en mémoire vive puis effacé. Aucun envoi externe, aucun stockage.

Drop a PDF, Word, Excel, PowerPoint or a photo (HEIC, JPG…) hereSign in to tryUp to 50 MB · 8,000 free credits a month · no card required

Measured quality

We publish the number. Check it yourself.

Everyone claims “accurate detection”. We publish ours, measured every morning against a corpus of one hundred legal documents, with the ground truth and the scoring script available for download. You don’t have to take our word for it — you can run it again.

Detection

97.5 %

of the details that should be masked are detected — measured on French legal documents. Dates are deliberately left readable: masking a limitation period or a length of service would make the document useless.

Corpus

100 documents

1,885 details to mask, ground truth included. Corpus, scoring rules and script available for download: run it again yourself.

Last measured

19 September 2026

The benchmark runs every morning. The trend and the per-type breakdown are public.

See the measurement

Pricing

Cheaper than a photocopy, per file.

Free

0 € / month

8,000 credits a month free (≈ 20 pages) — one credit per word of the document analysed, reset on the 1st

No card, no commitment

Every detection type, mapping included

Start for free
Launch offer · −50%

Prepaid credits

0,90 € HT / 100,000 credits

A 10-page contract costs about €0.04 excl. VAT

10 million credits: €90 €45 excl. VAT · valid 12 months

No subscription · processed in memory, nothing retained

Top up credits

Prices exclude VAT. VAT (20% in France) is added at checkout. EU businesses providing a valid VAT number are not charged it.

Privacy by design

What the AI never saw cannot leak.

It comes down to one sentence: the only data that is truly safe is the data that never left. Your document is processed and wiped within seconds — never stored, never read by a human, never used to train a model.

Hosted in the EUGDPR compliantNothing stored

What we never do

Write your document to a disk

Keep the mapping table

Log the contents in our records

Train an AI on your data

Sell or share anything

Set tracking cookies

Anonymisation runs in France, before anything is sent: the names in your documents are replaced by tokens there. Only those tokens cross the Atlantic to Claude or ChatGPT. The mapping table never leaves your machine.

For your technical team

Substitute before you call the AI.

One endpoint, a Node SDK and a Python SDK. Put it in front of your own AI calls: every response returns the exact count, so there are no surprises on the invoice.

POST https://lexform.zevra.tech/api/anonymize

-H "Authorization: Bearer <your-key>"

-F "file=@contrat.pdf"

→ substituted markdown + mapping + usage count

Frequently asked questions

What we are asked most often.

The questions a firm asks before installing, answered the way we answer them on the phone.

Do my documents reach Claude or ChatGPT in the clear?

No. The document is anonymised in France first: names, companies, addresses, IBANs and identifiers are replaced by tokens. Only those tokens cross the Atlantic. And if our engine does not answer, the message is blocked — nothing ever leaves in the clear.

Where is my data processed?

On a sovereign AI we host in France, in Gravelines. Your document does not leave European soil during anonymisation. Only the already-anonymised text reaches the AI you use.

Does lexform keep my documents?

No. Content is processed in memory and erased within seconds: nothing on disk, nothing in our logs, nothing in a training set. All we keep is a word count, which billing requires.

Who can recover the real names?

You alone. The table mapping each token to its original value stays in your browser: we never send it anywhere and keep no copy. We would therefore be unable to re-identify your documents, even if asked to.

Is this compatible with legal professional privilege?

lexform keeps the identity of your clients and their cases out of whatever leaves your machine, which is where the risk with generative AI lies. Privilege remains your personal duty: the tool reduces exposure, the judgement stays yours.

Are dates masked?

No, and that is deliberate. In legal work dates carry the reasoning: limitation periods, seniority, notice periods, deadlines. Masking them would make the document useless to the AI — precisely what you are trying to do with it. A date of birth therefore remains visible to the model.

How much does it cost?

Twenty pages a month are free, no card required. Beyond that you top up prepaid credits: one credit is one word of the analysed document. You pay only for what you send, and the balance is returned with every call.

Do I need to install anything?

The Chrome extension, from the Chrome Web Store, then a token to paste once. It sits between your browser and the AI: you write as usual, and anonymisation and restoration happen without any extra step.

Is this really anonymisation under the GDPR?

Strictly under the regulation, no: anonymisation there is irreversible, whereas here you can restore the real names. Technically this is pseudonymisation — and that is what you want for a case file: a document only you can unmask. We say “anonymisation” because that is the word everyone uses; the mapping table itself never leaves your machine.