artoo-corporation/D2-Python

Detect and Deny - Deterministic Function-Level Guardrails for AI Agents

/ 100

Emerging

This project helps software developers secure their AI applications by controlling what actions an AI agent can take. It allows you to define policies in a simple configuration file that specify which functions an AI can call, in what order, and with what arguments. The system takes these policy rules and enforces them at every step of the AI agent's execution, preventing unintended or malicious actions.

Use this if you are building an AI agent-driven application and need to ensure your AI only performs authorized actions, even when the AI itself decides the execution flow.

Not ideal if your application does not use AI agents or if you only need traditional security measures like API gateways or application firewalls.

AI-application-security Agent-governance LLM-security Access-control Application-security

No Package No Dependents

Maintenance 10 / 25

Adoption 6 / 25

Maturity 15 / 25

Community 9 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

—

Featured in

Agent Governance in 2026: Who's Building the Guardrails? Agent Platforms Are Four Problems, Not One Your Agent Doesn't Have an Email Address (Yet) Your Agent is Hitting its Ceiling — Who's Actually Fixing It

Higher-rated alternatives

ucsandman/DashClaw

🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...

Dicklesworthstone/destructive_command_guard

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being...

microsoft/agent-governance-toolkit

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...

vstorm-co/pydantic-ai-shields

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...

Pro-GenAI/Agent-Action-Guard

🛡️ Safe AI Agents through Action Classifier

Explore AI Agents

All categories Trending AI Agent directory Insights