Permanent redaction for compliance. Reversible sanitization for AI workflows. One API, two modes, zero exposure.
# 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
Permanent redaction for compliance. Reversible sanitization for AI. Same API, different outcomes.
PII is permanently removed. No session created. No recovery possible. Ship it to auditors, store it in logs, share it freely.
PII is replaced with safe placeholders. Send clean text to any LLM. Restore originals when you need them back.
Two API calls. That's it.
Send us text, we replace PII with safe placeholders.
Send the safe text to Claude, GPT-4, Gemini — whatever you want.
Send us the LLM response, we restore original values.
The more you use it, the smarter it gets.
Corrections train disambiguation rules. No retraining. No model updates. Deterministic.pip install ambientmetapip install langchain-ambientmetapip install llama-index-ambientmetaDrop-in wrapperDrop-in wrapperfrom langchain_ambientmeta import PrivacyGateway gateway = PrivacyGateway(api_key="am_live_xxx") safe_llm = gateway.wrap(your_llm) # PII handled automatically response = safe_llm.invoke("Summarize the file")
PII never touches external APIs. Self-hosted option available. Detailed audit logs for every request.
Create your account in 30 seconds. No credit card required.
Get Started Free