antropos17/Aegis
Open-source EDR for AI agents. Monitor processes, files, network, and behavior of autonomous AI agents.
Monitors the behavior of autonomous AI agents on your local machine, tracking what files they access, their network activity, and overall processes in real time. It takes raw system events from running AI agents and provides a clear, categorized view of their actions, flagging any suspicious behavior with a trust score. This tool is designed for anyone using or managing AI agents locally who needs to ensure they operate securely and within expected parameters.
Use this if you run autonomous AI agents on your local machine and need to monitor their activity, detect anomalies, and ensure they aren't accessing sensitive data or engaging in unauthorized network communications.
Not ideal if you are looking for an enterprise-level, cloud-based solution to monitor interactions between humans and AI via API, rather than agent behavior on a local endpoint.
Stars
94
Forks
15
Language
JavaScript
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/antropos17/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