Self-driving by design
Goal mode, wait/yield/resume, background sub-agents, and a monitor-goal cadence let it run an engagement unattended — and a watchdog recovers it when something stalls or crashes.
pwndeck · pen.protolabs.studio
Self-driving security engagements on a Steam Deck wired to RF, WiFi, and RFID — headless-first, scope-aware, and yours.
____ _ _ ____ ___ __ | _ \ ___ ___| | __ | '_ \ \ /\ / / '_ \| | | |/ _ \/ __| |/ / | |_) \ V V /| | | | |_| | __/ (__| < | .__/ \_/\_/ |_| |_|____/ \___|\___|_|\_\ |_|
$ systemctl --user start protopen
[pwndeck] online · :7870 · engagement ready
$ goal "recon the lab subnet, report criticals"
Goal mode, wait/yield/resume, background sub-agents, and a monitor-goal cadence let it run an engagement unattended — and a watchdog recovers it when something stalls or crashes.
Drives PortaPack H4M, Flipper Zero, WiFi Marauder, and BlackArch from a Steam Deck — RF, WiFi, and RFID assessments from one device you can carry.
Runs on your hardware against the models you host. Kill-chain phase gating and engagement scoping keep it inside the rules of engagement; goal verifiers never execute shell.
Headless-first, with a full operator console: chat, skills, playbooks, workflows, and findings. Drive it — or chain it to other agents — over A2A 1.0.
$ git clone https://github.com/protoLabsAI/protoPen && cd protoPen && python -m server Then follow the Steam Deck setup to wire up the hardware, or start with the getting-started tutorial.