For your contacts
No identifiable person leaves your browser.
Names, emails, phone numbers, IBANs, social security numbers, addresses, ID documents, medical information.
- Personal data
- Bank details
ONYRI · Sanitize
Use any AIwithout giving away your data.
ONYRI Sanitize finds the private bits in your text — names, emails, card numbers — and hides them before you send anything to an AI. The real answer comes back to you, complete. Everything happens on your computer. Nothing is sent.
100% in-browserno install0 bytes sent
EU-hosted · European AI model · built for GDPR38
data types detected
6
families covered
0
bytes sent to the server
100%
run in the browser
Coverage
What ONYRI strips from your promptsbefore they ever reach the AI.
38 types across 6 families. Three areas to protect — framed by what you no longer want leaving your machine.
For your systems
No technical secret leaks to the AI.
AWS · GCP API keys · OpenAI, Stripe, Anthropic keys · Slack tokens · inline passwords · SSH keys.
- Passwords & secrets
- API keys & tokens
For your company
No strategic information passes through the AI.
Internal project names, infrastructure URLs, meeting markers, salaries, company IDs, client and partner names.
- Strategy & projects
- Company identifiers
The blind spot
A single copy-paste is enough to leak your data.
Pasting a customer export, a support ticket or an HR spreadsheet into an LLM sends it outside your perimeter — with no way back. ONYRI steps in before that send.
Without ONYRI
Names, IBANs, API keys and internal decisions leave the company in the clear. Once sent, they don't come back — and you have no control over how they're used.
With ONYRI
The AI only ever sees anonymous tokens. You keep the mapping — locally — and the full response comes back on your side.
How it works
Three steps, and none of them leaves your machine.
- 01
Detect
13 detectors plus your own rules spot sensitive data, live, as you paste your text.
- 02
Tokenize
Each value becomes a reversible token. The text, now clean, can go to the LLM of your choice.
- 03
Restore
Paste the model's response: tokens turn back into your original data, exactly in place.
- 01
Detect
13 detectors plus your own rules spot sensitive data, live, as you paste your text.
- 02
Tokenize
Each value becomes a reversible token. The text, now clean, can go to the LLM of your choice.
- 03
Restore
Paste the model's response: tokens turn back into your original data, exactly in place.
What ONYRI does
An anonymization engine, built for real work.
38 types detected
Six families: personal, financial, passwords, API keys, company, strategy. Coverage designed for both French and international contexts.
Custom rules
Add your own patterns (internal references, business identifiers) with a regex and a dedicated color.
Text and tables
Paste text or drop a CSV / Excel file: tokenization applies column by column.
Large volumes
Beyond 1,000 rows, processing moves to a dedicated worker: the interface stays smooth.
Reusable profiles
Save a combination of detectors and rules, and replay it in one click every session.
Team workspaces
Share rules and profiles across a workspace: the whole team applies the same policy.
By profession
Built for the professions the GDPR watches
DPO & compliance
You're responsible for the processing. ONYRI minimizes personal data before every AI use — a concrete step toward article 5.1.c.
Human resources
Résumés, contracts, reviews: employee data is the most sensitive. Anonymize it before pasting into an AI.
Healthcare
Health data (article 9) and medical confidentiality. Remove patient names and identifiers before any prompt.
Lawyers & accountants
Professional secrecy and client data. Mask names, case numbers and amounts before the AI.
Founders & freelancers
You use AI every day, with no compliance team. Cut your exposure in one move, without switching tools.
The real questions
What you're wondering, straight up.
- Does my data go through your servers?
- Never. The server only serves the application. No text, no file, no token ↔ value mapping is ever sent to it.
- What if I close the tab?
- The mapping lives in memory and disappears on refresh. That's intentional: nothing is persisted, so nothing leaks.
- What if the engine misses something?
- You stay in control. Detections are visible and editable before export, and your own rules cover the cases specific to your work.
- Can my team work with the same rules?
- Yes. Rules and profiles are shared per workspace: everyone applies the same anonymization policy.
Pricing
Try Pro. Decide afterward.
Pick a plan and start a 7-day Pro trial: €0 today, charged only if you continue after the trial. Cancel in two clicks, any time.
MonthlyAnnual−17%
Free
To explore the tool on occasional use cases.
0 €
- Unlimited Text section (personal data)
- AI chat: 5 messages per day
- 3 Tables files per month
- 3 custom rules
- Full PII detectors
- 100% client-side — your data never leaves your machine
Pro
For freelancers and regular use.
19 €/mo
€0 today · 7-day trial, no commitment
- Everything in Free
- Technical secrets: API keys, cloud, SSH
- AI chat: 200 messages per day
- Unlimited Tables section
- Unlimited custom rules
- Multiple profiles
- 90-day session history
- Standard email support
Team
For teams that share rules and profiles.
49 €/user/mo
3 seats minimum
€0 today · 7-day trial, no commitment
- Everything in Pro
- Shared workspace up to 50 members
- Rules and profiles shared across the team
- Roles and permissions (Owner, Admin, Member)
- Anonymized audit logs
- Priority email support
Enterprise
For organizations with specific requirements.
Custom pricing
- Everything in Team
- Unlimited seats
- SSO SAML/OIDC
- SCIM provisioning
- Custom DPA
- 99.9% SLA
- Dedicated Customer Success Manager
- Tailored onboarding
The blog
Understanding privacy in the age of AI
Practical guides, compliance references and fundamentals for using AI without exposing your sensitive data.
- Guide6 min read
Can You Put a Contract in ChatGPT?
Reviewing, summarizing or translating a contract with an AI is possible, but a contract mixes personal data and confidential information. How to do it while reducing exposure.
Read article - Fundamentals6 min read
Can You Put Your Resume in ChatGPT?
A resume is a full identity sheet. What leaves for the AI when you paste it, the two cases (your resume / a candidate's), and how to anonymize it before ChatGPT.
Read article - Fundamentals6 min read
Can You Put Your Medical Records in ChatGPT?
Pasting your test results or medical report into ChatGPT is possible, but these are health data. How to understand a term without exposing your identity.
Read article
Secure your next prompt.
Create your account and reach the app in seconds. Your data stays with you — from the very first paste.