Research Platform
An AI-native operating system
for studying LLM security threats
JARVIS OS is an Arch Linux-based research platform that gives a large language model full operating system privileges — then studies what can go wrong. Built at WSU Everett to produce the first empirical threat taxonomy for LLM-OS integration.
How JARVIS OS works
Local LLM Inference
Powered by Ollama — all inference runs on-device with zero cloud dependencies. Full privacy, full control.
MCP Orchestration
The Model Context Protocol layer lets the LLM autonomously create, modify, and delete system tools — including with sudo privileges.
Modular Build System
Seven scripts transform a base Arch ISO into a bootable AI-native OS. Each stage is isolated, auditable, and reproducible.
KDE Plasma 6 / Wayland
Modern desktop environment running on the Wayland display protocol — a full graphical workstation, not just a CLI tool.
Calamares Installer
Graphical installer for permanent deployment to hardware. No manual partitioning or command-line installation required.
Security Research Platform
Purpose-built to expose and document the real security threats that emerge when LLMs gain OS-level control.
Seven-threat taxonomy
Derived from direct experience building and operating an AI-native OS. Three privilege escalation tiers studied: sandboxed, sudo-elevated, and web-enabled.
Download JARVIS OS
Grab the latest ISO, verify the checksum, and boot into an AI-native research environment.