Metadata-Version: 2.4
Name: aport-agent-guardrails
Version: 1.0.21
Summary: APort Agent Guardrail — shared core for AI agent and LLM frameworks (pre-action authorization)
Author: APort Technologies Inc.
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/aporthq/aport-agent-guardrails
Project-URL: Repository, https://github.com/aporthq/aport-agent-guardrails
Project-URL: Documentation, https://github.com/aporthq/aport-agent-guardrails/tree/main/docs
Project-URL: Issues, https://github.com/aporthq/aport-agent-guardrails/issues
Keywords: aport,agent guardrail,LLM guardrail,AI agent,guardrails,authorization,policy,agent security
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: PyYAML>=6.0
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pytest-asyncio; extra == "dev"

# aport-agent-guardrails

Shared Python runtime for APort guardrails.

This package provides:

- the core evaluator
- the generic `OAPGuardrailProvider`
- framework-agnostic config and policy mapping helpers

Framework setup and integration guides live in the main repository docs:

- https://github.com/aporthq/aport-agent-guardrails/tree/main/docs
- https://github.com/aporthq/aport-agent-guardrails/tree/main/docs/frameworks
