Metadata-Version: 2.4
Name: safentic
Version: 1.0.2
Summary: Safentic SDK for behavior analysis
Home-page: https://safentic.com
Author: Safentic
Author-email: contact@safentic.com
License: Proprietary :: Safentic Commercial License
Classifier: Programming Language :: Python :: 3
Classifier: License :: Other/Proprietary License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
Requires-Dist: requests
Requires-Dist: PyYAML==6.0
Requires-Dist: sentence-transformers==3.2.1
Requires-Dist: sqlalchemy
Requires-Dist: python-dotenv
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: summary

# Safentic SDK

Safentic is a runtime guardrail SDK for agentic AI systems.  
It intercepts and evaluates unsafe tool calls between agent **intent** and **execution**, enforcing custom safety policies.

---

## Installation

Install from PyPI:

    pip install safentic

---

## API Key Required

Safentic requires a valid API key to function.  
To obtain one, contact: contact@safentic.com

---

## Quick Start

```python
from safentic import SafetyLayer, SafenticError

layer = SafetyLayer(api_key="your-api-key", agent_id="agent-007")

try:
    layer.protect("send_email", {"body": "Refund me now!"})
except SafenticError as e:
    print("Blocked by policy:", e)
