Guard Lab: open-source 3D game where an LLM guards a safe and you try to rob it
flowersslop · x · 2026-10-12
Developer flowersslop released Guard Lab, an open-source 3D experiment where an LLM plays a safe-guard and you try to rob it — by lying, tricking it into revealing the code, or breaking in.
- Play as the thief, switch roles and play as the AI guard, or run AI-vs-AI experiments
- Works via the Codex app, other agent bridges, local models (e.g. Ollama), or compatible APIs
- Built on Electron + Three.js; runs on Windows/macOS/Linux, MIT licensed for forking and modding
More from coding & agent
- Community + AI agents push integer multiplication κ bound up 69% in a day via E8 geometry — CatAstro_Piyush · 2026-10-12
- AI agent deploys a micro factory end-to-end: €20k cost, ROI under 2 years — ihorbeaver · 2026-10-12
- Solo dev uses Claude to build open-source rivals to Adobe and Microsoft Office — mark_k · 2026-10-12
- xtool: open-source Xcode alternative builds and deploys iOS apps on Linux and Windows — sull · 2026-10-12
- Hermes Agent officially ships anatomy skill for wireframes and interactive prototypes — marktenenholtz · 2026-10-12
- One guy cataloged 263 real Grok Bot use cases from 870 replies — thisiskp_ · 2026-10-12