[PII REDACTION]

Stop sensitive data from reaching your LLMs.

Automatic PII detection and redaction in every request. Regex patterns catch structured data in under 1ms. Local AI models handle names, addresses, and context-dependent entities.

Get Started FreeDocs

What it does

Grepture scans every outbound request for sensitive data — emails, credit cards, API keys, names, addresses, and more — and redacts them before the request leaves your infrastructure. On the return path, redacted tokens are rehydrated so your app gets complete responses.

How it works

Detection rules run in the proxy layer. Free tier uses 50+ regex patterns for structured PII. Pro adds locally-hosted NER models for context-dependent entities like names and organizations, plus prompt injection detection. All processing happens on Grepture infrastructure — no data sent to external AI services.

app.grepture.com/rules
Rules5
+ New Rule
#RuleApply toSampleOn
1
Redact emails & phones
Both100%
2
Block prompt injections
Input100%
3
Mask API keys
Both100%
4
AI: Detect names & addressesAI
Both50%
5
Log sensitive requests
Input25%
Redact emails & phones
rule_01H8K...
Actions
Redact PII
emailphonessncredit_card
Find & Replaceinternal-key-* → [REDACTED]
Configuration
Apply to
InputOutputBoth
Sampling rate
100%
Conditions
Match all requests

Key features

  • [+]50+ regex patterns for emails, SSNs, credit cards, API keys, and more
  • [+]Local AI models for names, organizations, and addresses (Pro)
  • [+]Prompt injection detection and blocking (Pro)
  • [+]Token rehydration — your app gets complete responses
  • [+]Custom regex patterns and named rules (Pro)
  • [+]Per-endpoint and per-model policy overrides (Pro)

Start observing your AI traffic in 5 minutes

Drop-in SDK. See your first request in under a minute.

Free for up to 1,000 requests/month · No credit card required

Get Started Free