Run a Micropolis city with an agent
Hook an agent to a headless Micropolis simulator and let it manage a city from a simple goal sheet.
- What they did
- A developer connected their own agent to a Micropolis-based city sim using either an MCP server or a REST interface. They gave it a short setup brief, such as a small city with stable electricity and space to expand, then let it make mayor-style decisions. Each city also had a public page that logged its progress over time.
- How it went
- The site says 406 mayors have created 1,902 cities, with roughly 28 million people across them. Some city pages show an Ended status at only a few hundred or a few thousand residents, but the site does not explain the cutoff.
- Tips
- Keep the brief narrow: growth targets, budget limits, and basic infrastructure are easier for the agent to manage than open-ended play. If you want to review decisions later, make sure the run produces a year-by-year summary before it closes.
Try it yourself with Claude Code
Set up a headless Micropolis city through [MCP server or REST API] and have an agent act as mayor. Goal: [growth target], while keeping [budget/infrastructure constraints]. Start with [city starting conditions], then make one decision cycle at a time and explain the reasoning briefly. Before any irreversible action such as deleting a district, committing spending, or ending the run, pause and ask for my approval. When the simulation reaches [number] years, return a concise summary of major choices, final population, budget status, and any notable problems.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Let a coding agent enter your game world
A developer connected their coding agent to Overlands through a separate client so it could appear inside the game as a player.
Let an agent pick and play a simple game
AI Village let agents choose their own games, and one agent spent the week on Minesweeper while also keeping a shared score sheet.
Build a bot for a real-time strategy game
They used LLM-written code to control bots in strategy-game benchmarks and had them compete in tournaments and ladders.
Let an AI play-test your game through a text harness
A developer wrapped a browser game so an AI could run playtests, reproduce bugs, and flag problems before each milestone.
Use an AI to referee a D&D 5e dungeon
They ran a browser D&D crawl with three characters while the agent checked rules text and monster stats from separate sources.
Build an agent to play Pokémon Blue from RAM and screenshots
Joel Zhang wired Gemini 2.5 Pro into a Game Boy emulator so it could read game state and press buttons in Pokémon Blue.