antropos17/Aegis
Open-source EDR for AI agents. Monitor processes, files, network, and behavior of autonomous AI agents.
Detects and scores 107 AI agent signatures in real time using behavioral baselines, 68 customizable detection rules, and 4-axis anomaly scoring—all running locally with zero cloud dependency. Built as an Electron desktop app (Svelte 5, TypeScript) for Windows/macOS/Linux, it monitors 27 AI agent config directories, reverse-DNS classified network connections, and local LLM runtimes (Ollama, LM Studio, vLLM), assigning trust grades (A+ through F) via time-decay risk algorithms and optional Anthropic API threat assessment.
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
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
vstorm-co/pydantic-ai-middleware
Middleware layer for Pydantic AI — intercept, transform & guard agent calls with 7 lifecycle...
mattijsmoens/sovereign-shield
AI security framework: tamper-proof action auditing, prompt injection firewall, ethical...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...