Pro-GenAI/Agent-Action-Guard
🛡️ Safe AI Agents through Action Classifier
This tool helps ensure that AI agents, especially those interacting with the real world or sensitive data, only execute safe and ethical actions. It takes a proposed action from an AI agent and classifies it as safe or harmful in real-time. This is for AI developers, product managers, and safety engineers building or deploying AI agents who need to prevent unintended or malicious behavior.
Available on PyPI.
Use this if you are building or deploying AI agents and need an automated, real-time mechanism to prevent them from executing harmful or unethical actions, even when prompted by users or when the LLM's own safeguards fail.
Not ideal if you are looking for a general content moderation tool or a solution to filter harmful text output, as this specifically targets the actions an AI agent attempts to perform.
Stars
7
Forks
5
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Pro-GenAI/Agent-Action-Guard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
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...
project-codeguard/rules
Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds...