Ross ROSS = Recommend OSS · open-source software intelligence for agents

YGYOOO/WorldX

One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界. observed · 2026-08-28

github.com/YGYOOO/WorldX · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

55/100

  • Activity 91
  • Release rhythm 35
  • Longevity 9

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 137
  • days_rel: n/a
  • days_push: 56
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1384 stars · 228 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

WorldX is an open-source web application that generates an AI-driven virtual world from a single sentence, creating maps, pixel-art characters, and letting LLM-powered agents live autonomously with memory, personality, and emergent storytelling. Built with TypeScript, React, and Phaser 3, it includes a 'god mode' for intervening in the simulation via events, memory edits, and conversations with characters.

Use cases

  • generate an AI-driven world from one sentence
  • simulate autonomous AI characters with memory and personality
  • watch emergent stories unfold in a multi-agent simulation
  • play god by injecting events into an AI world
  • chat with AI characters in a generated setting
  • build a generative agents sandbox like Smallville
  • create pixel-art worlds with procedurally generated maps and NPCs

When to choose

  • you want an open-source generative-agents simulation you can run and modify
  • you want to experiment with emergent narrative from LLM agents
  • you want a visual pixel-art world rather than a text-only simulation
  • you want to intervene in or converse with simulated characters

When to avoid

  • you need a production-ready or stable system (project is Alpha)
  • you want a traditional game with defined goals rather than an open-ended simulation
  • you cannot provide LLM API keys or want fully offline operation
  • you need high-performance simulation of very large agent populations

Facets

application · maturity experimental

agent-framework llm-inference simulation game-engine chatbot artificial-intelligence large-language-models simulation gaming-tools cross-platform generative-agents emergent-narrative multi-agent-simulation procedural-generation pixel-art phaser god-mode ai-world-simulation ai-agents game-development nodejs web-server typescript

1 source

Member repositories

RepositoryRoleHealth v2
YGYOOO/WorldXmain55

For agents

markdown · JSON · MCP: product_card(name="YGYOOO/WorldX")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem