aporthq/aport-agent-guardrails

Pre-action authorization guardrails for AI agents - Works with OpenClaw, Claude Code, LandChain, CrewAI and others

37
/ 100
Emerging

This project helps engineering and product teams ensure their AI agents operate safely and within defined permissions. It takes an agent's intended action as input and checks it against a security policy before execution, preventing unauthorized or risky operations. The end-users are AI developers, security engineers, and product managers responsible for deploying and managing AI agents.

Use this if you need to prevent AI agents from performing unintended or harmful actions, especially in sensitive environments or when agents have access to external tools.

Not ideal if you are looking for a general-purpose AI agent framework or if your agents do not interact with external tools or sensitive data.

AI-security agent-governance LLM-operations authorization-policy AI-risk-management
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 11 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Shell

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/aporthq/aport-agent-guardrails"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.