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.

What it solves

WorldX allows users to create a fully functional, simulated virtual world from a single sentence description. It eliminates the need for manual world-building, character scripting, or map design by using AI to generate the environment, inhabitants, and the emergent stories that unfold between them.

How it works

The system uses a pipeline of four specialized AI roles to bring a world to life:

  1. Orchestrator: Designs the world structure, rules, and character profiles based on the user's prompt.
  2. Image Generation: Creates the visual assets for the map and character portraits.
  3. Vision: Reviews the generated map quality and identifies specific regions or elements.
  4. Simulation: Drives the runtime behavior of AI agents, managing their decision-making, dialogue, and memory.

These agents live in a pixel-art world (powered by Phaser 3 and React) where they autonomously interact, form relationships, and evolve over day-night cycles. Users can act as a "God," intervening by broadcasting events or editing character memories.

Who it’s for

It is designed for creators, storytellers, and AI enthusiasts who want to experiment with emergent narratives, autonomous agent simulations, and procedural world generation.

Highlights

  • One-Sentence Creation: Generates a complete world, including maps and characters, from a simple text prompt.
  • Autonomous Agents: Characters make their own decisions, remember past experiences, and develop unique behavioral patterns.
  • God Mode: Allows users to inject events, modify personalities, or engage in hypothetical dialogues with characters.
  • Timeline System: Supports the creation of multiple divergent timelines within the same world.
  • Multi-Model Support: Compatible with various LLMs and image generators via OpenAI-compatible APIs or Google AI Studio.

Related

  • Project
    AMAP-ML/DreamX-World

    DreamX-World is a general-purpose interactive world model that generates high-fidelity, controllable simulations allowing users to explore and transform environments via event prompts.

  • Project
    ZJU-LLMs/OpenStory

    A multi-agent simulation framework that uses LLMs to create interactive story worlds, featuring the ability to generate entire simulated environments from a single natural language prompt.

  • Project
    4thfever/cultivation-world-simulator

    An AI-driven cultivation world simulator where every NPC is an independent LLM agent, creating an emergent narrative based on a rigorous set of cultivation rules.

  • Project
    ZiYang-xie/WorldGen

    WorldGen is a tool that generates immersive 3D scenes from text prompts or images in seconds, supporting both Gaussian Splatting and mesh outputs for VR, games, and simulations.

  • Project
    EmergenceAI/Emergence-World

    A persistent, simulated world where autonomous AI agents with unique personalities and memories build societies, govern themselves, and evolve over time to study emergent behaviors.