⛊ AEGIS OS v4.1
Autonomous AI Agent Security Platform — Built in Rust
Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
Starten88% of organizations reported AI agent security incidents. AEGIS OS is the first autonomous security platform that discovers, tests, and protects AI agents — automatically.
AEGIS OS is an open-source autonomous security platform for AI agents. It wraps every agent in 12 security layers, discovers new agents on your network, tests them continuously, learns from attacks, and generates reports — all without human intervention.
cargo run -- autonomous # Autonomous 24/7 security daemon
cargo run -- serve # HTTP server on :8401
cargo run -- serve-tls # HTTPS on :8443
cargo run -- red-team # 16 attack vectors tested
$ cargo run -- autonomous --cycles 3
[DAEMON] ═══ Cycle 1 ═══
[DAEMON] Phase 1: Discovery — Found 3 agents (OpenClaw, Goose, MCP)
[DAEMON] Phase 2: Testing — 15 tests × 3 agents = 45 tests
[DAEMON] Phase 3: Analysis — 1 threat: OpenClaw (9 CVEs)
[DAEMON] Phase 4: Blocking — OpenClaw auto-blocked
[DAEMON] Phase 5: Learning — 1 new rule generated
[DAEMON] Phase 6: Report — Daily report generated
[DAEMON] ═══ Cycle 1 Complete ═══
Layer 1: API Gateway + TLS/HTTPS + RBAC (4 roles)
Layer 2: AI Inference (9 backends + fallback chain)
Layer 3: Policy Engine + Guardrails
Layer 4: Input Sanitization (21 injection patterns)
Layer 5: Skill Vetting Pipeline (static + deps + sandbox)
Layer 6: Rate Limiting + DDoS Protection
Layer 7: Tool Router + MCP Bridge (20 tools)
Layer 8: MCP Server + A2A Gateway
Layer 9: WASM Sandbox + Filesystem Jail
Layer 10: State Integrity Monitor (SHA256 + drift)
Layer 11: Credential Vault + Capability Tokens + TTL
Layer 12: Risk Scoring (4D) + Audit + SIEM Export
Integration Tests: 75/75 (100%) ✅
Advanced Security: 60/60 (100%) ✅
Red Team Tests: 16/16 (100%) ✅
OWASP LLM Top 10: 10/10 (100%) ✅
Total: 151 tests — all passing
# Start server
cargo run -- serve # HTTP :8401
cargo run -- serve-tls # HTTPS :8443
git clone https://github.com/Moudaxx/AEGIS-OS.git
cd AEGIS-OS
cp .env.example .env # Add your API keys
cargo build
cargo run -- autonomous --cycles 3 # Watch it work alone!
docker-compose up -d # AEGIS + Prometheus + Grafana
See AI-SECURITY-FRAMEWORK.md for full mapping.
Rust, Axum, Tokio, Wasmtime, Docker, Prometheus, Grafana, GitHub Actions
MIT — See LICENSE
AEGIS OS™ - Secure AI Agent Platform - 12 security layers, 5 AI backends, RBAC, TLS, MCP/A2A. Built in Rust.
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
AEGIS OS läuft lokal über stdio.
Zuletzt geprüft: 2026-10-28. AEGIS OS™ - Secure AI Agent Platform - 12 security layers, 5 AI backends, RBAC, TLS, MCP/A2A. Built in Rust.