Professional AI-powered penetration testing framework with autonomous agents, 72+ integrated security tools, and real tool execution. Built for security professionals, bug bounty hunters, and enterprise teams.
Commits
Security Tools
AI Personas
Evolution Phase
Risk Levels
Open Source
Reason → Act → Observe → Reflect pattern with autonomous decision making, self-correction, and memory management for complex pentest workflows.
Specialized agents: Recon, Exploit, Report, Audit, Social Engineering, Network, Mobile, Red Team, ICS, Cloud, and Crypto experts.
IP validation (blocks private networks), domain filtering, 4-level risk system (Safe to Aggressive), and rate limiting for safe operation.
Workflow orchestrator manages complex pentest workflows with task distribution, real-time WebSocket updates, and result aggregation.
Native Kimi AI integration plus OpenRouter, OpenAI, Anthropic support with intelligent routing based on task complexity.
ProtonVPN native CLI integration plus generic OpenVPN/WireGuard detection with safety warnings and strict mode options.
One-command deployment with docker-compose, isolated environments, multi-agent scaling, health checks, and production-ready configuration.
High-performance REST API with WebSocket support, JWT authentication, role-based access control, and automatic API documentation.
CVSS/EPSS scoring, false positive reduction, business impact calculation, and automated finding prioritization.
# Clone repository
git clone https://github.com/SHAdd0WTAka/zen-ai-pentest.git
cd zen-ai-pentest
# Install dependencies
pip install -r requirements.txt
# Configure environment
cp .env.example .env
# Edit .env with your API keys
# Start full stack
docker-compose up -d
# Check status
docker-compose ps
# Scale agents
docker-compose up -d --scale agent=3
from agents.react_agent import ReActAgent, ReActAgentConfig
# Configure agent
config = ReActAgentConfig(
max_iterations=10,
use_vm=True,
vm_name="kali-pentest"
)
# Create and run
agent = ReActAgent(config)
result = agent.run(
target="example.com",
objective="Security assessment"
)
# Start API server
uvicorn api.main:app --reload
# API will be available at http://localhost:8000
# Documentation at http://localhost:8000/docs