By George Curta · Last updated 2026-04-07
Supported Sites
The anonym.legal Chrome Extension works with 6 AI chatbot platforms. Each site requires explicit host permission to be enabled via the extension popup.
Compatibility Table
Status reflects testing as of v1.1.37. "Fully Working" sites have been verified with automated Playwright tests. "Requires Enable" sites need host permission activation per browser profile.
| Site | Domain | Status | Bridge | Connector | Notes |
|---|---|---|---|---|---|
| DeepSeek | chat.deepseek.com | Fully Working | Ready | Attached | Full functionality. Bridge establishes automatically, connector attaches to the chat input. |
| Perplexity | perplexity.ai | Fully Working | Ready | Attached | Full functionality. Bridge establishes automatically, connector attaches to the chat input. |
| Gemini | gemini.google.com | Fully Working | Ready | Attached | Full functionality. Uses rich-textarea element detection with optimized height threshold. |
| ChatGPT | chatgpt.com | Requires Enable | Not set | Not loaded | Host permission must be enabled per-profile via the extension popup. Once enabled and the page is refreshed, full functionality is available. |
| Claude | claude.ai | Partial | Not set | Loaded | Connector loads but bridge timing requires a page refresh. SPA navigation between /new and /chat paths is handled with cache preservation. |
| Abacus.ai | abacus.ai | Ready | Untested | Untested | Connector is available and ready. Site-specific integration has been implemented. |
DeepSeek
Fully Workingchat.deepseek.com
Full functionality. Bridge establishes automatically, connector attaches to the chat input.
Perplexity
Fully Workingperplexity.ai
Full functionality. Bridge establishes automatically, connector attaches to the chat input.
Gemini
Fully Workinggemini.google.com
Full functionality. Uses rich-textarea element detection with optimized height threshold.
ChatGPT
Requires Enablechatgpt.com
Host permission must be enabled per-profile via the extension popup. Once enabled and the page is refreshed, full functionality is available.
Claude
Partialclaude.ai
Connector loads but bridge timing requires a page refresh. SPA navigation between /new and /chat paths is handled with cache preservation.
Abacus.ai
Readyabacus.ai
Connector is available and ready. Site-specific integration has been implemented.
How It Works
The extension operates in three stages to protect your personal data when interacting with AI chatbots.
Detect Text in Chat Input
When you type or paste text into an AI chatbot's input field, the extension detects the content. It uses site-specific connectors that understand each platform's editor (including ProseMirror editors used by Claude and others).
Anonymize Before Sending
The extension steps in before your message reaches the AI platform. It swaps personal data (names, emails, phone numbers, addresses, and 285+ entity types) for placeholders. The AI never sees your real data.
De-anonymize Responses
When the AI responds, the extension automatically replaces the anonymized placeholders with your original data. You see the full, meaningful response while the AI platform only ever processed anonymized text.
MV3 Optional Host Permissions
The extension is built with Manifest V3 and uses optional_host_permissions. This is Chrome's recommended approach for extensions that only need access to specific websites.
Required Permission
anonym.legal -- Always required. Used for authentication and API communication. This is the only permission the extension requests at install time.
Optional Permissions (user-enabled)
Each AI site is an optional permission. You choose which sites to enable:
- chatgpt.com -- ChatGPT
- claude.ai -- Claude
- gemini.google.com -- Gemini
- chat.deepseek.com -- DeepSeek
- perplexity.ai -- Perplexity
- abacus.ai -- Abacus.ai
File Anonymization
In addition to chat text, the extension can anonymize files before uploading them to AI platforms. Supported file types:
.txtPlain text files.mdMarkdown files.csvComma-separated values.jsonJSON data files.xmlXML documents.yamlYAML configuration.logLog filesFile size limit: Maximum 50KB per file. For larger files, use web app batch processing or the Desktop App. Some AI sites block direct file upload. The extension then offers a "Copy anonymized text" fallback so you can paste the content by hand.
About this page
We update this page when our platform or the law changes.
Read our founder note for how we work.
Each change shows up in the timestamp at the top.
Related reading
- Common questions
- Glossary
- How tokens work
- Security posture
- Where we comply
- What we detect
- Case studies
- Release notes
We follow these rules
- GDPR (EU 2016/679).
- ISO/IEC 27001:2022.
- NIS2 (EU 2022/2555).
- HIPAA safe harbor under 45 CFR § 164.514(b)(2).
Our promise
We do not sell your data.
We do not train models on your text.
We store your files in Germany.
You can delete your account at any time.
You own your work.
Where we run
Our servers live in Falkenstein, Germany.
We use Hetzner. They hold ISO 27001 certification.
All data stays in the EU.
Backups run every day.
Need help?
Email support@anonym.legal.
We reply within one business day.
How we test
We run a full check suite on every release.
Each surface gets its own sweep script and report.
Human reviewers spot-check the output each week.
We track recall and precision on a labelled set.
Bad runs block the deploy.
What we never do
- We never sell your information to third parties.
- We never train models on what you upload.
- We never keep your work after you delete it.
- We never share keys with any outside firm.
- We never run ads inside the product.
Plans in plain words
We sell credits, not seats.
One credit covers one short job.
Long jobs use a few credits each.
You can top up at any time.
Unused credits roll over each month.
Read the plans page for current rates.
Who built this
A small team of engineers and lawyers built this.
We ship from Europe and work in the open.
Our founder note spells out why we started.
Where to start
- Open the web app and try a sample file.
- Learn how credits get counted.
- See current plans and limits.
- Meet the team behind the product.
How the parts fit
A browser add-on cleans text inside Chrome.
A Word plug-in handles drafts in Office.
A small desktop tool works on whole folders.
An agent protocol link feeds large models safely.
All four share one core engine and one rule set.
Words from our team
We started this work after a lunch about cookies.
One friend kept getting odd ads on her phone.
We asked why a court file leaked through a draft.
We sketched the first build on a napkin that week.
By month three we had a tiny demo for a friend.
She used it on her first case the next day.
Common questions we hear
Can the tool read scanned PDFs? Yes, with OCR.
Does it work on long files? Yes, in small chunks.
Can I roll my own rule set? Yes, save it as a preset.
Does it run offline? The desktop build runs offline.
Do you keep my files? No, the cloud build wipes after each run.
Will it learn from my work? No, we never train on inputs.
A short tour of the workflow
Upload a file or paste a snippet of prose.
Pick the entities you want gone from the draft.
Choose a method: replace, mask, hash, encrypt, or redact.
Press run and watch the side panel show each hit.
Skim the result and tweak any rule that misfired.
Save the cleaned file or send it to a teammate.