AEGIS-OS

# ⛊ AEGIS OS v4.1

**Autonomous AI Agent Security Platform — Built in Rust**

[![Release](https://img.shields.io/github/v/release/Moudaxx/AEGIS-OS)](https://github.com/Moudaxx/AEGIS-OS/releases)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
[![Tests](https://img.shields.io/badge/Tests-135%2F135-brightgreen)]()
[![OWASP](https://img.shields.io/badge/OWASP_LLM_Top_10-10%2F10-brightgreen)](AI-SECURITY-FRAMEWORK.md)

> 88% of organizations reported AI agent security incidents. AEGIS OS is the first autonomous security platform that discovers, tests, and protects AI agents — automatically.

## What is AEGIS OS?

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.
```bash
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
```

## Autonomous Mode — Works Alone
```
$ 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 ═══
```

### 6-Phase Autonomous Cycle

| Phase | Engine | What it does |
|-------|--------|-------------|
| 1. Discover | Discovery Engine | Scans ports, MCP servers, Docker containers |
| 2. Test | Continuous Testing | 15 security tests per agent |
| 3. Analyze | Threat Analysis | Risk scoring + known CVE matching |
| 4. Block | Auto-Block | Blocks agents above risk threshold |
| 5. Learn | Adaptiv