Your clients’ data doesn’t belong in ChatGPT.
Now it doesn’t have to.
Stript finds and replaces personal data in your documents — names, addresses, IBANs, everything — so you can use any AI tool without compliance risk. Runs entirely on your machine. Purpose-built for German and English documents.
See it in action
Stript detects personal data and replaces it with consistent pseudonyms — automatically.
Dear Dr. James Wilson [PERSON_1] ,
following our meeting on March 14, 2026, I am sending you the documents regarding the case Anderson [PERSON_2] v. Miller [PERSON_3] (Ref. 4 O 123/26).
Please transfer the amount of $15,000.00 to account DE89 3704 0044 0532 0130 00 [IBAN_1] .
Kind regards,
Sarah Mitchell [PERSON_4]
[email protected] [EMAIL_1]
Tel: +1 212 555 7890 [PHONE_1]
This happens entirely on your machine. No cloud. No API. Just local AI.
The privacy gap in AI adoption
It’s happening in your organization right now.
68%
of employees use AI tools at work
52%
paste sensitive data into ChatGPT
€20M+
in GDPR fines issued in 2025 alone
Right now, someone in your organization is pasting a client contract into ChatGPT. An HR report into Claude. A financial audit into Gemini. They know the risks — they do it anyway, because the productivity gain is irresistible.
You can’t ban AI. But you can make it safe.
How it works
From sensitive document to safe AI usage in under 60 seconds.
Upload or paste
Drop in a PDF, DOCX, or paste text directly. Stript reads it locally — nothing leaves your machine.
AI detects personal data
Stript’s AI scans your document in seconds. Names, email addresses, phone numbers, IBANs, and more — found automatically with over 95% accuracy.
Review & confirm
Every detection is highlighted in context. Confirm, reject, or reclassify with one click. You stay in control.
Use any AI tool safely
Copy the anonymized text to ChatGPT, Claude, or any LLM. Paste the AI response back — Stript restores the original data instantly.
Real AI on your machine — not another cloud wrapper
Most anonymization tools cut corners. Stript doesn’t.
Simple find & replace
Basic tools search for keywords and patterns. They miss names in context, catch false positives, and can’t tell ‘Berlin’ the city from ‘Berlin’ the client.
Cloud AI service
Some tools send your documents to an API for analysis. That defeats the purpose — your sensitive data still leaves your machine and lands on someone else’s server.
On-device NLP that understands context
Stript runs multiple AI models directly on your computer. It analyzes sentence structure, understands context, and knows the difference between a person’s name and a city. No data leaves your machine — ever.
Three analysis layers. Zero cloud dependencies. Every model runs on your hardware.
Who is Stript for?
Built for professionals who handle sensitive data every day.
Data Protection Officers
Give your teams a compliant way to use AI — instead of fighting a losing battle against shadow IT.
Lawyers & Legal Teams
Summarize contracts, draft letters, analyze case law with AI — without exposing client data.
Consultants & Advisors
Process client reports and financial documents through AI tools without breaching confidentiality agreements.
IT & Compliance
Deploy a solution your teams will actually use — because it integrates into their existing workflow, not against it.
Built for privacy-conscious professionals
Everything you need to use AI without compromising sensitive data.
Your data never leaves your machine
Stript downloads AI models once, then runs fully offline. Your documents are analyzed by real NLP models running on your hardware — not sent to a cloud API. You can verify this: disconnect from the internet and Stript keeps working.
Understands context, not just keywords
Stript doesn’t just search for patterns — it understands language. It knows ‘Dr. Weber’ in a greeting is PII but ‘Weber’ as a profession isn’t. Three independent analysis layers cross-check each detection: structural pattern matching, named entity recognition, and contextual classification. All running locally.
Get your original data back in one click
Consistent pseudonyms like [PERSON_1] and [EMAIL_1] throughout your document. Paste the AI response back — every name, address, and IBAN is restored exactly.
Works with your existing documents
PDF, DOCX, or plain text. Upload a file or paste directly. Stript handles the extraction automatically.
Bank-grade encryption for mappings
The link between original data and pseudonyms is encrypted with AES-256-GCM. Keys are stored in your operating system’s secure keychain.
Catches what manual review misses
Benchmarked against real legal and financial documents. Pattern matching finds structured data with 99%+ accuracy. AI catches the rest.
How Stript compares
No more compromises between privacy and productivity.
| Feature | Stript | CamoText | Manual Review |
|---|---|---|---|
| AI-powered detection | Partial | ||
| Context-aware classification | |||
| German language support | Limited | Manual | |
| Reversible anonymization | |||
| Multi-format (PDF, DOCX) | Text only | Manual | |
| Runs 100% locally | |||
| Encrypted mapping storage | — | ||
| >95% recall | Varies |
Frequently asked questions
Everything you need to know about how Stript handles your data.
Is my data really processed locally?
Yes, completely. Stript runs multiple AI models directly on your hardware — not through a cloud API. You can verify this yourself: disconnect from the internet after the initial model download, and Stript works exactly the same. No document content ever touches a server. The only network requests are the one-time model download and optional update checks.
What data does Stript collect?
Stript collects no document content, no personal data, and no usage telemetry. The only data we store is your waitlist email (if you sign up) and encrypted anonymization mappings on your local machine.
How accurate is the PII detection?
Our three-stage detection pipeline achieves over 95% recall on real-world legal and financial documents. Structured data like emails, IBANs, and phone numbers are detected with 99%+ accuracy. You always review and confirm before anonymization.
Which file formats are supported?
Stript supports PDF, DOCX, and plain text files. You can upload a file or paste text directly. Scanned (image-only) PDFs are not yet supported — OCR is on our roadmap.
Can I use Stript in my law firm or company?
Absolutely. Stript is designed for professional use in regulated industries. The Enterprise plan includes self-hosted deployment via Docker, team management, and SSO/SAML integration. Your IT department stays in full control.
Is Stript GDPR-compliant?
Yes. Since all data processing happens locally on your machine, no personal data is transferred to third parties. Stript is privacy-by-design — there is no data processing agreement needed because we never see your data.
Simple, transparent pricing
Start free. Upgrade when you need more.
Free
Try Stript with no commitment.
- 10 documents per month
- All detection types
- PDF, DOCX & text support
- 100% local processing
Professional
For professionals who handle sensitive data daily.
- Unlimited documents
- Priority model downloads
- Advanced detection profiles
- Project management
- Email support
Enterprise
Self-hosted or cloud. For teams and organizations.
- Everything in Professional
- Self-hosted deployment (Docker)
- Team management
- SSO / SAML integration
- Custom entity types
- Dedicated support & SLA
Stop choosing between productivity and privacy.
Join the waitlist and be among the first to try Stript. We’ll notify you as soon as early access opens.