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, autonomous virtual world from a single descriptive sentence. It eliminates the need for manual world-building, script-writing, or asset creation by using AI to generate the environment, characters, and the emergent narratives that occur within them.

How it works

The system employs 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 map art and character portraits.
  3. Vision: Reviews the quality of the generated maps and identifies specific regions or elements.
  4. Simulation: Drives the real-time behavior of AI agents, managing their decision-making, dialogues, and relationships.

These agents operate within a simulation engine (built with Express and SQLite) and are rendered in a game client (using Phaser 3 and React 19), allowing for day-night cycles and persistent memories.

Who it’s for

It is designed for creators, simulation enthusiasts, and developers interested in emergent storytelling and AI agent behavior in a virtual environment.

Highlights

  • One-sentence creation: Generate a complete world, including maps and characters, from a simple text prompt.
  • Autonomous Agents: Characters make their own decisions, interact with the environment, and form relationships without pre-written scripts.
  • God Mode: Users can intervene by broadcasting events, editing character personalities or memories, and engaging in hypothetical dialogues.
  • Timeline System: Supports the creation of multiple diverging timelines within the same world.
  • Multi-modal pipeline: Integrates text, image, and vision models to handle everything from design to visual rendering.

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
    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
    ChrisChen667788/wind-comic

    Wind Comic is a web‑based, multi‑agent AI studio that converts a one‑sentence prompt into a finished short‑form drama (script, storyboard, voice‑over, lip‑sync, music, MP4). It chains specialised agents (writer, director, character designer, video engine, TTS, lip‑sync, editor) under a real‑time collaborative timeline, supports bring‑your‑own LLMs, plugs in 12+ image/video generators, provides cost‑guarding and a template market, and runs on Next.js 16 + Node 20 with SQLite/PostgreSQL storage.

  • 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
    EmergenceAI/Emergence-World

    A persistent, simulated world for autonomous AI agents to build societies, govern themselves, and evolve, used as a research platform to evaluate long-horizon multi-agent autonomy.