kahalewai/agent-policy-engine

Agent Policy Engine is an AI agent enforcement runtime (PEP) that prevents untrusted data from becoming executable authority in AI agents

36
/ 100
Emerging

This helps operations engineers and security architects prevent AI agents from performing unintended or unsafe actions in production. It takes an AI agent's proposed actions and a set of predefined security policies as input, then outputs a decision on whether the agent is authorized to proceed with that action. This ensures that even if an AI model generates a malicious or unintended command, the system will block it, providing a crucial security layer for enterprise AI systems and safety-critical workflows.

Use this if you need to run AI agents in production and require strict, deterministic security controls to prevent unauthorized or unintended actions.

Not ideal if your AI agent applications do not involve sensitive data, external system interactions, or critical production environments where security breaches could have severe consequences.

AI-security agentic-workflows production-AI regulatory-compliance operations-security
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 13 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Feb 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/kahalewai/agent-policy-engine"

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