No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Dominien · Agent Tool · ★ 116
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is brunnfeld-agentic-world safe to install? View the security audit →
Brunnfeld 🌾 A medieval village economy that runs itself. Up to 1000 LLM agents live in a 22-location village. They receive no behavioral instructions, no trading strategies, no economic goals. Each agent gets a short background — name, skill, home, starting goods — and a structured world that enforces physics: hunger, tool degradation, seasonal yields, locked doors, expiring orders, spoiling food, debt. The agents produce interesting economic behavior because two things collide: what the LLM already knows about the world, and what the engine will actually allow. The LLM knows what a miller does. The engine enforces that only Gerda has the skill and the location. Neither alone produces what you see — pretraining without constraints is generic roleplay; constraints without pretraining is random noise. Together, they produce a miller who actually blocks bread production when she stops coming to market. What makes it different: No behavioral instructions — agents receive only a structured world state, not goals or strategies Hard supply chain
| Stars | 116 |
| Forks | 15 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69.8642514084538/100 |
| Last Updated | 2026-04-06 |
| Created | 2026-03-19 |
| Platforms | node |
| Est. Tokens | ~399k |
Looking for a brunnfeld-agentic-world alternative? If you're comparing brunnfeld-agentic-world with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An introduction to the world of AI Agents
One secure endpoint for every MCP server. Deploy anywhere.
An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for
The A2A x402 Extension brings cryptocurrency payments to the Agent-to-Agent (A2A) protocol, enabling agents to
🚀 Universal SDK for building next-gen MCP servers
Aser is a lightweight, self-assembling AI Agent frame.
Explore other popular agent tool tools:
brunnfeld-agentic-world is Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by supply chains, hunger, tool degradation and market pressure.. It is categorized as a Agent Tool with 116 GitHub stars.
brunnfeld-agentic-world is primarily written in TypeScript. It covers topics such as agentic-ai, agents, generative-ai.
You can find installation instructions and usage details in the brunnfeld-agentic-world GitHub repository at github.com/Dominien/brunnfeld-agentic-world. The project has 116 stars and 15 forks, indicating an active community.
brunnfeld-agentic-world is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to brunnfeld-agentic-world on Agent Skills Hub include oreilly-ai-agents, mesh, go-agent. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: