Metadata-Version: 2.4
Name: piiguardrails
Version: 2.0.0
Summary: Enterprise PII Guardrail Studio
Project-URL: Homepage, https://github.com/piiguardrails/piiguardrails
Project-URL: Repository, https://github.com/piiguardrails/piiguardrails
Requires-Python: >=3.8
Description-Content-Type: text/markdown

# Enterprise PII Guardrails Studio

Enterprise PII Guardrail Studio is a high-performance, enterprise-grade AI safeguard gateway designed to detect, mask, redact, and pseudonymize Personally Identifiable Information (PII) before it reaches Large Language Models (LLMs) or third-party APIs.

## Key Features

- **Blazing Fast Masking**: Sub-25ms sustained masking latency with in-memory caching and background async audit logging.
- **Enterprise-Grade Privacy**: Detects 30+ sensitive entities including SSN, Credit Cards, IBAN, Passports, API keys, Names, Addresses, Medical IDs, and more.
- **Encrypted Storage**: Local audit logs and security telemetry secured with SQLCipher AES-256 encrypted database.
- **Hardware-Locked Licensing**: Anti-tampering, node-locked hardware integrity verification.
- **Zero-Footprint Cleanup**: Automatic orphaned temp purging prevents `%TEMP%` disk bloat across repeated runs.
- **Modern Management UI**: Material Design 3 / MUI dashboard for live telemetry, access keys, policy rules, and audit logs.

## Quickstart

### Installation

```bash
pip install piiguardrails
```

### Launching the Studio

```bash
piiguardrails
```

On first run, the core engine will automatically initialize and launch the local API server and management dashboard at:
```
http://127.0.0.1:8000
```

### API Usage Example

Once the studio is running, integrate it directly into your Python LLM pipeline:

```python
import requests

API_KEY = "your-api-key-here"  # Generated via Studio UI
headers = {"X-API-Key": API_KEY, "Content-Type": "application/json"}

payload = {
    "text": "Hello John Doe, your verification code was sent to john.doe@acme.corp",
    "risk_level": "MODERATE",
    "policy": "anonymize"
}

response = requests.post("http://127.0.0.1:8000/mask", json=payload, headers=headers)
print(response.json())
# Output: {"masked_text": "Hello <PERSON_1>, your verification code was sent to <EMAIL_ADDRESS_1>", ...}
```

## System Requirements

- **OS**: Windows 10 / 11 / Windows Server (64-bit)
- **Python**: >= 3.8

## License

Proprietary / Enterprise Commercial License. All rights reserved.

