Proxia by Anankelis — local inspection, masking suggestions, your decision.
On-device · data firewall for AI

Catch the secret before it reaches the AI.

You paste a stack trace, a config file, a client's email into ChatGPT — and an API key or an IBAN rides along. Proxia inspects every prompt on your own device, masks what's sensitive, and restores it in the reply. Nothing is ever sent to a server.

Proxia prevents secrets and personal data from reaching AI tools, locally, before sending.

No account, licence server, payment method or product telemetry.

Watch — it's already inspecting the panel. Type your own, or load an example.

chatgpt.com
try:
Checkpoint
Use cases

Sensitive information is part of your work.

Find your workflow, then explore the situations that matter to your profession.

The part that matters

Most "AI DLP" tools have to see your text. Proxia never does.

To check a prompt, a cloud filter has to receive it first — so your secrets pass through someone else's server on the way to being "protected." Proxia's engine runs inside your browser. The comparison is the whole product:

Cloud AI-DLP

Your text leaves to be checked.

You──▶their server──▶The AI

A second copy of every prompt now lives somewhere you don't control. The tool meant to protect your data is itself a place it can leak.

Proxia

Your text is checked in place.

You──▶Proxia · on-device──▶The AI

A pure Rust core compiled to WebAssembly inspects the prompt locally. No telemetry, no beacons. The only thing that ever leaves is what you decide to send.

What it catches

Trained on the things you'd regret pasting.

Regex plus algorithmic validation — Luhn, IBAN mod-97, national-ID checksums — keeps false positives low. A random 16-digit number isn't a card unless it checks out.

Secrets // critical

API keys and tokens, private-key blocks, passwords in config, connection strings.

  • sk-…, AKIA…, ghp_…
  • -----BEGIN PRIVATE KEY-----
  • PASSWORD=…
  • high-entropy strings

Financial // high

Bank details validated, not just pattern-matched.

  • IBAN (mod-97)
  • Card number (Luhn)

Identity // personal

National IDs with real checksums, plus contact data.

  • French SSN (NIR)
  • Belgian national number
  • International phone
  • Email

Manipulation // injection

Not just your data leaving — attacks coming in.

  • Prompt-injection phrasing
  • Hidden Unicode / bidi
  • Phishing signals
The checkpoint

Three moments, one decision.

01 — write

You compose as usual

Type or paste into ChatGPT, Claude, Gemini — whatever you already use. Proxia stays out of the way.

02 — check

Inspected the instant you send

In ~40 ms, on-device, before a single byte leaves. If it's clean, you never notice.

03 — decide

Send masked, send anyway, or cancel

One click swaps secrets for tokens and restores them in the reply. Your call, every time.

No telemetry

No analytics, no beacons, no phone-home. Your prompts are never transmitted anywhere.

Your settings stay local

Manage protection settings on your device without sharing your prompts or inspection results with ANANKELIS SAS.

Non-destructive

Proxia flags, masks, and proposes. It never silently deletes your text — you keep the last word.

Beyond the prompt

It guards the tools your AI calls, too.

Agents don't just chat — they run shell commands, send email, hit APIs. A secret leaks through a tool call's arguments. Proxia inspects those and blocks a credential heading into a dangerous tool — on the browser, and directly on the MCP tool-call path.

Where it works

Supported AI services.

Keep control of sensitive data when you use AI. Find the setup that fits your browser in the installation guide.

Installation and compatibility

ChatGPTClaudeGemini Microsoft CopilotMCP · local stdio only
Where it runs

Choose the protection that fits your tools.

Features and availability vary by platform. Check the guide for the version you install.

Free and Plus

Free protects browser traffic to LLMs, agents and APIs. Plus adds Gmail, Outlook web, unlimited personal terms and web-page masking.

Pro

Desktop Outlook and email clients, Excel analysis and masking, automatic rule updates and individual dashboards.

Enterprise

All Pro features, central policy management, optional technical reporting, centralized logs, export and an educational portal.

Straight answers

The questions you're already asking.

Does it slow me down?
No. The check runs in about 40 milliseconds, on-device, at the moment you send. If your prompt is clean you never see anything.
What about false positives?
Detectors that can be validated are validated — a card must pass Luhn, an IBAN must pass mod-97, a national number must match its checksum. And with per-site profiles you can quiet a category on a specific site. Critical secrets are always flagged regardless.
Is my data really safe?
Inspection runs locally in your browser. Your text is not sent to ANANKELIS SAS for analysis. Review the proposed protected text before sending it to the AI service you use.
Which languages does it cover?
The interface is available in French, English and Dutch. Detection of identifiers such as IBANs and card numbers does not depend on the interface language. Detection based on wording varies by language.
What can't it see?
The browser extension protects supported websites. It does not inspect native AI desktop applications. The MCP guard supports local stdio connections only; HTTP/SSE and remote MCP are not supported. Other Proxia versions have their own installation guides and limitations.

Get started with Proxia.

Install the free browser extension, or explore the setup options for Outlook, Git and local MCP servers.