AAPP-MART

AI-Autonomous Attack Path Prediction & Multi-Agent Red Team Simulation Engine

AAPP-MART is an AI-Autonomous platform for attack simulation, threat modeling, and autonomous red team operations aligned with MITRE ATT&CK.

Predict. Simulate. Secure.

Get Started on GitHub

About

AAPP‑MART (AI‑Autonomous Attack Path Prediction & Multi‑Agent Red Team Simulation Engine) is an open‑source Python security engine designed for offensive security research, adversarial modeling, and automated risk assessment. It combines AI‑powered attack‑path prediction with autonomous multi‑agent red‑team simulation to model how real attackers navigate an environment and to reveal actionable, data‑driven security insights.

Unlike traditional static vulnerability scanners or manual penetration testing, AAPP‑MART uses predictive analytics, graph‑based threat modeling, and autonomous adversarial behavior to deliver continuous and realistic security evaluation. Its architecture helps defenders anticipate attack strategies, validate defensive controls, and understand real‑world risk through repeatable, scalable, and intelligence‑driven simulations.

The system generates structured attack-path reports, MITRE ATT&CK-mapped insights, and risk scoring outputs to support SOC operations, detection engineering, and continuous security improvement.

Why AAPP-MART?

AAPP-MART stands out from traditional security tools in its approach:

Traditional scanners → static, reactive, often limited to known vulnerabilities.
BAS (Breach & Attack Simulation) tools → rely on predefined playbooks and limited scenarios.
AAPP-MART → predictive, autonomous, and adaptive: forecasts attack paths and executes intelligent multi-agent simulations.

By combining AI-Autonomous Attack Path Prediction with Multi-Agent Red Team Simulation Engine, AAPP-MART provides organizations with a forward-looking security posture, not just reactive alerts.

Use Cases

AAPP-MART enables advanced, intelligence-driven security operations through the following core use cases:

Predictive Attack Path Analysis
Autonomous Red Team Simulation
Attack Surface & Lateral Movement Modeling
MITRE ATT&CK–Aligned Threat Simulation
Vulnerability Prioritization & Risk Scoring

How it Works

AAPP (AI-Autonomous Attack Path Prediction)
Evaluates assets, configurations, permissions, and vulnerabilities to predict probable attacker paths.
MART (Multi-Agent Red Team Simulation Engine)
Autonomous agents simulate realistic adversary actions: Reconnaissance, Exploitation, Lateral Movement, Privilege Escalation, Persistence, Reporting
CORE Orchestration Engine
Coordinates AAPP & MART, maintains a global knowledge graph, executes simulations, and produces structured risk reports.

Example Attack Flow:

[User Credential] → [Phishing/Exploit] → [Initial Access] → [Lateral Movement] → [Privilege Escalation] → [Critical Asset Compromise]

Architecture

The system is architected around three primary subsystems:

AI-Attack Path Prediction Engine (AAPP)
Multi-Agent Red Team Simulation Engine (MART)
Core Orchestration Layer

These subsystems operate in a tightly integrated manner through a shared attack graph (knowledge graph), enabling coordinated attack modeling, adversarial simulation, and unified risk analysis across the platform.

Legal & Authorized Use Only

AAPP-MART is intended solely for authorized security assessment, defensive threat modeling, and controlled adversary simulation within environments where explicit permission has been granted.

The system is designed for non-destructive analysis and does not support uncontrolled exploitation. Users are fully responsible for ensuring compliance with all applicable laws, regulations, and organizational policies when operating this system.

Unauthorized use of this system is strictly prohibited and may violate applicable laws and regulations.

Legal Disclaimer

The developers and contributors of this project assume no responsibility or liability for misuse, damage, or legal consequences arising from the use of this software.

This software is provided “as is” without warranty of any kind, express or implied.

Who is this for

CISOs, InfoSec managers, and executive stakeholders seeking actionable security intelligence
Security, engineering, and risk teams aiming to proactively assess and improve cyber resilience
Internal/External red, blue, and purple teams requiring realistic, repeatable adversary emulation
Organizations subject to regulatory or compliance mandates (MITRE ATT&CK, NIST, CIS, PCI DSS, ISO 27001, etc.)

Features

AI-Autonomous Attack Path Prediction
Multi-Agent Red Team Simulation Engine
Graph-based threat modeling and attack graph analysis
MITRE ATT&CK aligned adversary behavior modeling
Risk-based security posture analysis
ML-assisted vulnerability prioritization

Conceptual Usage Example

This example reflects the intended public API design:

import os
from aapp_mart.core.orchestrator import AAPP_MART

# Initialize the engine with a target IP or hostname
engine = AAPP_MART(target="")

# Run simulation
engine.run()

# Retrieve the generated attack-path report
report = engine.get_report()

# Print a concise summary of the predicted attack paths
report.export(format="json", path="./logs/attack-path/attack_report_.json")

See API Reference for interface details.

Demo

Run the AAPP-MART CLI simulation locally:

python demo/demo.py

Output Example

=== AAPP-MART Demo ===
[!] Running in DEMO MODE (package not installed)

[+] Target: 192.168.1.10
[+] Simulating attack path prediction...
[+] Running adversarial simulation...
[✓] Simulation completed
[+] Report exported → ./logs/attack-path/attack_report_192.168.1.10.json

Run on Google Colab

Launch the interactive demo here:

Attack Path Demo Notebook on Google Colab

Colab Output

Environment is ready for AAPP-MART demo.
Simulating attack path prediction for target: 192.168.1.10
Report exported in json format to ./logs/attack-path/attack_report_192.168.1.10.json

NOTE:

DEMO: This IP/hostname is an example target. You will write the actual target IP/hostname yourself in the main project.

Installation

Supported Operating Systems

Windows 10 / 11
Linux (Ubuntu 22.04+, Debian 11+)
macOS (Intel and Apple Silicon)

Requirements

Python 3.11+
pip 23+

Quick Start

# Clone repo
git clone https://github.com/secwexen/aapp-mart.git
cd aapp-mart

# Create virtual environment
python -m venv venv
source venv/bin/activate  # Linux/Mac
venv\Scripts\activate     # Windows

# Install dependencies
pip install -r requirements.txt

# Install dev dependencies
pip install -r dev-requirements.txt

For full details, refer to the Quick Start file.

Docs & Resources

Community & Support

Contribute code, documentation, or testing. CONTRIBUTING.

Join Discussions to share feedback and proposals.

Check out for tasks and ideas. Open an issue.