Cultivation World Simulator

Active
GitHub Python NOASSERTION

Description

An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world. Showcases multi-agent collaboration in complex scenarios.

Key Features

  • Every NPC is an independent LLM-driven agent with unique personality, memory, relationships, and decision-making logic
  • Emergent storytelling with no preset scripts — sect wars, rivalries, and character arcs arise from world rules and AI interactions
  • Rich cultivation world system including spirit roots, realms, techniques, sects, alchemy, artifacts, and martial tournaments
  • Play as the Heavenly Dao — observe the world, descend tribulations, or subtly intervene in the simulation
  • Full-stack architecture with FastAPI backend, Vue.js frontend, and PixiJS rendering
  • REST API for external agent integration with query and command endpoints for observation and intervention

Use Cases

💡 Experience an AI-driven Xianxia world simulation where every character acts autonomously
💡 Study emergent multi-agent behavior and narrative generation in a rule-based world
💡 Build custom interventions and scenarios using the external control API
💡 Explore AI collaboration patterns through sect management and character interactions
💡 Deploy a Docker-based simulation environment for world-building experiments

Tags

multi-agent workflow agent python

Categories

🔄 Workflow 🧠 Multi-Agent

Quick Start

Clone the repo, install Python 3.10+ and Node.js 18+ dependencies, run `python src/server/main.py --dev` to start both backend and frontend, then configure a model preset (DeepSeek/MiniMax/Ollama) in the settings page before starting a new game.
Visit GitHub

Related Projects