Detect and redact PII from any text. Instantly.

Permanent redaction for compliance. Reversible sanitization for AI workflows. One API, two modes, zero exposure.

Try it live Type or paste text with personal data
Input
Sanitized
# Redact — permanent PII removal:
clean = ambientmeta.sanitize("Patient: John Smith, SSN 123-45-6789", mode="redact")
# clean.text → "Patient: [PERSON_1], SSN [SSN_1]"  (PII gone forever)

# Sanitize — reversible for LLM workflows:
safe = ambientmeta.sanitize("Summarize John Smith's file at john@acme.com")
reply = your_llm(safe.text)  # LLM sees placeholders, never real data
final = ambientmeta.rehydrate(reply, safe.session_id)  # restores originals

Two modes. One detection engine.

Permanent redaction for compliance. Reversible sanitization for AI. Same API, different outcomes.

mode: "redact"

AmbientMeta Redact

PII is permanently removed. No session created. No recovery possible. The data is gone. Ship it to auditors, store it in logs, share it freely.

For: FOIA processing, DSARs, compliance exports, log scrubbing, document redaction
"SSN: 123-45-6789" → "SSN: [SSN_1]"
permanent — no rehydration
Compliance, Legal, Government
or
mode: "sanitize"

Sanitize + Rehydrate

PII is replaced with safe placeholders. Send the clean text to any LLM. Restore original values when you need them back. Sessions expire after 24 hours.

For: LLM workflows, chatbots, RAG pipelines, summarization
"John Smith" → [PERSON_1] → LLM → [PERSON_1] → "John Smith"
Engineering Teams, AI Developers

How It Works

Two API calls. That's it.

1

Sanitize

Send us text, we replace PII with safe placeholders.

"Email John at john@acme.com"
→ "Email [PERSON_1] at [EMAIL_1]"
2

Call Any LLM

Send the safe text to Claude, GPT-4, Gemini—whatever you want.

reply = your_llm(safe.text)
3

Rehydrate

Send us the LLM response, we restore original values.

"Sure, I'll email [PERSON_1] at [EMAIL_1]"
→ "Sure, I'll email John at john@acme.com"
Your App
Sanitize
External LLM
Rehydrate
Your App

No code? No problem.

AmbientMeta Privacy Guard for Chrome

Detect and strip PII directly in ChatGPT, Claude, and Gemini. No API key needed. No code changes. Install, sign in with Google, and go.

  • Works on ChatGPT, Claude, and Gemini
  • One-click sanitize before you send
  • 50 free scans per day
  • Google sign-in, nothing else required
  • Real-time entity highlighting
Add to Chrome
AmbientMeta Privacy Guard
Entities detected3
Today's scans12 / 50
PERSON EMAIL PHONE
Sanitize Selected Text

What we detect

Standard PII, healthcare identifiers, and anything custom you define.

Standard PII

Person Names John Smith Email john@acme.com Phone (555) 123-4567 SSN 123-45-6789 Credit Card 4532-xxxx-xxxx-9012 Location New York, NY Address 123 Main St

Healthcare

NPI 1234567890 MRN Medical Record # DEA AB1234567

Custom

Your Patterns EMP-123456, PROJ-2026-A, ...

Define any regex pattern via the /v1/patterns endpoint

The more you use it, the smarter it gets.

Every correction teaches the system something new about your data.

1

Detect

PII identified via regex, NER, and compiled rules

2

Correct

You flag what we got wrong

3

Learn

Contradictions reveal ambiguity patterns

4

Compile

Rules are validated and deployed

5

Improve

Runtime accuracy increases automatically

←——————————————————————————→

When you correct a misclassification — a phone number that's actually an NPI — the system detects the contradiction, extracts what distinguishes the two contexts, formulates a disambiguation rule, validates it against known-good examples, and compiles it into the runtime engine. Next time, it gets it right. No retraining. No model updates. Deterministic rules compiled from your corrections.

Works with everything you already use.

First-class Python SDK. Drop-in wrappers for popular frameworks.

Python SDK

pip install ambientmeta

LangChain

pip install langchain-ambientmeta

LlamaIndex

pip install llama-index-ambientmeta

OpenAI

Drop-in wrapper

Anthropic

Drop-in wrapper
from langchain_ambientmeta import PrivacyGateway

gateway = PrivacyGateway(api_key="am_live_xxx")
safe_llm = gateway.wrap(your_llm)

# Use normally — PII handled automatically
response = safe_llm.invoke("Summarize the employee file")

Simple, predictable pricing.

Start free. Pay as you grow. No credit card required.

Free

$0
For evaluation
  • 1,000 requests/month
  • All entity types
  • Chrome extension (50/day)
  • Community support
Get Started

Developer

$29/mo
For startups & indie teams
  • 25,000 requests/month
  • All entity types
  • Custom patterns
  • Email support
Start Free Trial

Scale

$299/mo
For high-volume workloads
  • 500,000 requests/month
  • Everything in Team
  • Dedicated support
  • SLA guarantee
Start Free Trial

AmbientMeta Redact

Enterprise-grade redaction for compliance, legal, and government teams. Page-based pricing starting at $199/month. Same detection engine, built for document workflows.

FOIA Processing DSAR Compliance Document Redaction e-Discovery Self-Hosted & Air-Gapped
Contact Sales From $199/mo — 95% cheaper than manual redaction
SOC 2 Type II HIPAA Ready GDPR Compliant PCI-DSS Safe

Finally, AI your security team will approve.

Data sovereignty without building infrastructure. Or deploy on your own — same API, air-gapped, data never leaves your network.

🔒

PII Never Leaves

Sensitive data stays in your control. The LLM only sees placeholders.

🌐

Data Sovereignty

Self-hosted option for maximum control. Deploy in any region.

📋

Audit Ready

Detailed logs for every request. SOC 2 Type II in progress.

Frequently Asked Questions

What LLMs does this work with?

All of them. Claude, GPT-4, Gemini, Llama, Mistral—we're model-agnostic. We work at the text level, so any LLM that accepts text input works.

How accurate is the detection?

95%+ for standard entities out of the box. Our intelligence system learns from your corrections — flag a mistake, and the system formulates disambiguation rules so it doesn't happen again. Custom patterns can achieve 99%+.

What about HIPAA/PCI/GDPR?

Designed for compliance. PII never touches external APIs. We detect healthcare identifiers (NPI, MRN, DEA) out of the box. Self-hosted option for maximum control. SOC 2 Type II certification in progress.

What's the latency?

Less than 20ms p50 for sanitize, less than 5ms for rehydrate. Fast enough that users won't notice.

Can I define custom entity types?

Yes. Use the /v1/patterns endpoint to add detection for employee IDs, project codes, or any org-specific identifiers via regex.

Is there a self-hosted option?

Yes. Same API, your infrastructure. Single Docker image. Air-gapped deployments supported. Contact sales for pricing.

Ready to stop leaking sensitive data?

Create your account in 30 seconds. No credit card required.

Get Started Free