Justin0504/Aegis
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
AEGIS acts as a 'firewall' for AI agents, preventing them from executing harmful or unauthorized actions. It intercepts every tool call your agent makes, automatically classifies it (e.g., database, file, network), and enforces policies to block risky operations like SQL injection or data exfiltration. This tool is designed for anyone managing AI agents who needs to ensure their automated systems operate safely, securely, and within defined guardrails.
200 stars.
Use this if you need to add a crucial layer of security and control to your AI agents, ensuring they don't perform dangerous or unintended actions without human oversight.
Not ideal if you are looking for a tool solely for logging or observing agent actions after they happen, as AEGIS focuses on pre-execution prevention.
Stars
200
Forks
13
Language
TypeScript
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Justin0504/Aegis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
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