mundix-cli 2.3.2

AI-Powered Cybersecurity Copilot for Kali Linux — Think Claude Code, but built for hackers.

MundiX CLI

AI-Powered Autonomous Pentesting Agent for Kali Linux

MundiX CLI is an intelligent terminal-based pentesting copilot for penetration testers, red teamers, and security researchers. It features a multi-tier AI architecture with specialized models for planning, exploitation, and analysis — all routed through the MundiX backend API.

Think of it as an AI agent that actually runs your pentest — not just suggests commands.

---

Features

Feature	Description
Autonomous Agent	Full autonomous pentesting with 6-phase methodology (recon → exploitation → reporting)
AI Chat	Interactive conversation with specialized cybersecurity AI models
Multi-Agent	Parallel skill execution with coordinator + specialist agents
23 Skills	Pre-built attack skills (nmap, sqlmap, nuclei, hydra, etc.)
Smart Auto-Fix	Auto-installs missing tools, retries with sudo, evades WAFs
Knowledge Graph	Builds attack graph of discovered hosts, ports, vulns, creds
Threat Intel	Enriches findings with NVD CVEs, ExploitDB, CISA KEV
5-Level Autopilot	From manual confirmation to full autonomy
Safety Checks	Command whitelist, destructive command blocking, scope validation
Streaming	Real-time token streaming for fast responses

---

Quick Install (Kali Linux)

curl -sSL https://raw.githubusercontent.com/k0k4/mundix-cli/main/install.sh | bash

Manual Install

git clone https://github.com/k0k4/mundix-cli.git
cd mundix-cli
pip3 install -r requirements.txt
python3 mundix_cli.py

Install via pip

pip3 install -e .
mundix

Activation

After install, activate your device at https://mundix.dev/activate or run:

mundix --activate

You get 3 free queries before registration is required.

---

Usage

Interactive Mode

mundix

One-Shot Query

mundix "how to scan for open ports on 10.0.0.1"

Autonomous Pentest

Inside the interactive shell:

/agent example.com web

Choose a Model

mundix --model mx-strategist-72b

---

AI Models (Multi-Tier Architecture)

Key	Model	Tier	Description
mx-strategist-72b	MX-Strategist 72B	Brain	Strategic planner — pentest orchestration & deep analysis
mx-deephat-7b	MX-DeepHat 7B	Specialist	Offensive specialist — exploit generation & attack chains
mx-swift-3b	MX-Swift 3B	Executor	Fast executor — parsing, formatting & quick decisions
mx-minitron-8b	MX-Minitron 8B	Backup	Fallback model for high availability

---

CLI Commands

Inside the interactive shell, use these slash commands:

Command	Description
/help	Show help message
/agent <target> [type]	Start autonomous pentest (types: web, internal, app)
/models	List available AI models
/model <name>	Switch to a different model
/memory	Show memory statistics
/clear	Clear conversation history
/system	Show system information
/history	Show command execution history
/exec <cmd>	Execute a command directly
/analyze	Send last command output to AI
/exit	Exit MundiX CLI

---

Autonomous Agent — 6-Phase Methodology

1. Reconnaissance — OSINT, subdomain discovery, email harvesting
2. Scanning & Enumeration — Port scanning, service detection, directory discovery
3. Vulnerability Analysis — CVE search, vulnerability scanning, SSL/TLS analysis
4. Exploitation — SQL injection, brute force, file upload exploits, Metasploit
5. Post-Exploitation — Privilege escalation, lateral movement, hash cracking
6. Reporting — MITRE ATT&CK mapping, executive summary generation

---

Project Structure

mundix-cli/
  mundix_cli.py          # Main CLI application (REPL, Rich TUI)
  ai_provider.py         # MundiX Backend API integration
  agent_orchestrator.py  # Autonomous pentest brain
  multi_agent.py         # Multi-agent parallelism coordinator
  skill_loader.py        # Skill markdown parser and registry
  autopilot.py           # 5-level autonomy control
  playbooks.py           # Pre-defined attack methodologies
  knowledge_graph.py     # Attack graph for findings
  findings_db.py         # SQLite findings database
  threat_intel.py        # CVE/exploit enrichment
  memory.py              # Engagement memory/persistence
  system_integrator.py   # System interaction layer
  osint_monitor.py       # OSINT monitoring
  project.py             # Project/engagement state management
  skills/                # 23 skill definition files (.md)
  install.sh             # Quick installer for Kali Linux
  requirements.txt       # Python dependencies
  setup.py               # pip install support

---

Requirements

• Python 3.8+
• Linux (optimized for Kali Linux)
• MundiX account (free tier: 3 queries, register for more)

---

License

MIT License - MundiX

---

Built with purpose by MundiX. Happy Hacking.