# 4thfever/cultivation-world-simulator

基于 AI Agent 工作流的修仙世界模拟器，旨在还原智能、开放的仙侠世界。| An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world.

Repository: https://github.com/4thfever/cultivation-world-simulator
Canonical: https://ross.abutalabs.com/products/cultivation-world-simulator
Language: Python
License: NOASSERTION
License Family: other
Topics: agentic-workflow, ai, ai-agents, cultivation, game, llm, open-source, prompt-engineering, python, simulation, simulation-game, simulator, text-based-game, world-simulation, ai-native, autonomous-agents, procedural-generation, cultivation-game
Last push: 2026-08-16T11:21:40+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 96, longevity 27
- inputs: {"age_days": 380, "days_push": 17, "days_rel": 31, "gap_med": 4, "n_releases_24m": 40}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2042, forks 227 (observed 2026-08-28T04:06:08.560466+00:00)

## What it is
An open-source AI-driven Cultivation (Xianxia) world simulator where every cultivator NPC is an independent LLM-powered agent that observes the environment and makes decisions. The player acts as the 'Heavenly Dao', observing or subtly intervening in an emergent world shaped by both AI agents and a strict rule system.

## Use cases
- simulate an AI-driven xianxia cultivation world
- watch LLM agents form relationships and emergent stories
- play as the heavenly dao and intervene in a simulated world
- experiment with agentic workflows for world simulation
- study autonomous LLM agents in a rule-constrained game
- run a text-based AI sandbox game locally or via Docker

## When to choose
- you want an AI-native simulation game with fully LLM-driven NPCs
- you want to observe or research emergent multi-agent narratives
- you want a self-hostable or Docker-deployable AI game you can modify
- you're interested in agentic workflow examples in Python

## When to avoid
- you need a traditional hand-crafted RPG with scripted quests
- you can't access LLM API services or afford token costs
- you need a lightweight game that runs without AI backends
- you require a permissive license for commercial reuse (license is non-standard)

## Facets
- artifact type: application
- maturity: active
- function: simulation, agent-framework, llm-inference, game-engine, prompt-engineering, chatbot
- domain: artificial-intelligence, large-language-models, simulation, gaming-tools
- platform: python, cross-platform
- tags: xianxia, cultivation-game, world-simulation, emergent-narrative, text-based-game, ai-native, procedural-generation, autonomous-agents, fastapi, vue, pixijs, ai-agents, game-development, docker, desktop, web-server

## Member repositories
- 4thfever/cultivation-world-simulator (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.560466+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:58:17.232332+00:00, confidence not recorded.
  - readme: https://github.com/4thfever/cultivation-world-simulator (fetched 2026-08-28T04:06:08.560466+00:00, sha 3083d84486f1)
- Data as of 2026-08-30T08:39:29.467469+00:00.