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.
Stars: 884
Cultivation World Simulator is an AI-driven open-world cultivation simulator where players take on the role of 'Tian Dao' (God) to observe and influence the world of cultivators. The simulator features AI-driven NPCs with unique personalities, memories, and behaviors, a detailed world system based on cultivation elements like spiritual roots and techniques, emergent storytelling without predefined scripts, and a focus on creating a truly immersive cultivation world experience.
README:
This project now supports English. Don't hesitate to give it a try!
— ✦ —
一个AI驱动的修仙世界模拟器,旨在创造一个真正活着的、有沉浸感的仙侠世界。
这是一个 AI 驱动的开放世界修仙模拟器。
不同于传统的 RPG 扮演某个角色,在这里,你将扮演“天道”(上帝)。 你不需要亲自打怪升级,而是以上帝视角观察众生,在规则与 AI 共同编织的开放世界中,见证门派兴衰与天骄崛起。你可以静观沧海桑田,也可以降下天劫或魔改心灵,微妙地干预世界进程。
- 👁️ 扮演“天道” (上帝视角):你不是修士,而是掌控世界规则的天道。观察众生百态,体味苦辣酸甜。
- 🤖 全员 AI 驱动:每个 NPC 都独立基于LLM驱动,都有独立的性格、记忆、人际关系和行为逻辑。他们会根据即时局势做出决策,会有爱恨情仇,会结党营私,甚至会逆天改命。
- 🌏 规则作为基石:世界基于灵根、境界、功法、寿元等严谨的数值体系运行。AI 的想象力被限制在合理的修仙逻辑框架内,确保世界真实可信。
- 🦋 涌现式剧情:开发者也不知道下一秒会发生什么。没有预设剧本,只有无数因果交织出的世界演变。宗门大战、正魔之争、天骄陨落,皆由世界逻辑自主推演。
|
|
|
修仙网文中的世界很精彩,但读者永远只能观察到一隅。
修仙品类游戏要么是完全的预设剧本,要么依靠人工设计的简单规则状态机,有许许多多牵强和降智的表现。
在大语言模型出现后,让“每一个角色都是鲜活的”的目标变得似乎可以触达了。
希望能够创造出纯粹的、快乐的、直接的、活着的修仙世界的沉浸感。不是像一些游戏公司的纯粹宣传工具,也不是像斯坦福小镇那样的纯粹研究,而是能给玩家提供真实代入感和沉浸感的实际世界。
如果您对项目有任何问题或建议,欢迎提交 Issue 或 Pull Request。
欢迎给我的B站账号留言!
也可以加入QQ群进行讨论:1071821688。进群问题的答案:肥桥今天吃什么
加入 Discord 社区:https://discord.gg/shhRWmZR
如果你已经安装了 Docker,这是最简单的方式:
-
克隆项目
git clone https://github.com/AI-Cultivation/cultivation-world-simulator.git cd cultivation-world-simulator -
启动服务(自动构建并运行)
docker-compose up -d --build
-
克隆项目到本地:
git clone https://github.com/AI-Cultivation/cultivation-world-simulator.git cd cultivation-world-simulator -
安装依赖:
# 后端依赖 pip install -r requirements.txt # 前端依赖 (需Node.js环境) cd web && npm install
-
配置LLM:
推荐方式:在前端直接配置(支持快速填充预设)
也可以在
static/local_config.yml中手动配置(OpenAI兼容格式):llm: base_url: https://api.deepseek.com # API地址 key: your-api-key-here # 你的API密钥 model_name: deepseek-chat # 智能模型名称 fast_model_name: deepseek-chat # 快速模型名称 mode: default # 运行模式 (default/normal/fast)
本地部署 (Ollama): 也支持对接本地 Ollama,在前端选择 "Ollama (本地)" 预设即可。
-
运行:
# 启动服务 (推荐开发模式,会自动启动前端) python src/server/main.py --dev浏览器会自动打开网页前端。
无论使用哪种方式运行,启动后都可以通过以下地址访问:
前端:http://localhost:8123
后端 API:http://localhost:8002
支持从局域网内的其他设备(如手机、平板)访问游戏。
⚠️ 注意:移动端 UI 目前未做适配优化,体验可能不佳。详见 Issue #130。
配置步骤:
-
在
static/local_config.yml中添加:system: host: "0.0.0.0" # 允许局域网访问
-
如果使用开发模式(
--dev),还需在web/vite.config.ts的server配置中添加:server: { host: '0.0.0.0', // 添加这一行 proxy: { ... } }
-
启动服务器后,在手机浏览器访问:
http://<电脑局域网IP>:5173 # 开发模式 http://<电脑局域网IP>:8002 # 生产模式 -
查看电脑局域网 IP:
# macOS ipconfig getifaddr en0 # Linux hostname -I # Windows ipconfig
💡 确保手机和电脑连接同一个 WiFi,且防火墙已放行对应端口。
如果你觉得这个项目有趣,请给我们一个 Star ⭐!这将激励我们持续改进和添加新功能。
更多贡献细节请查看 CONTRIBUTORS.md。
- ✅ 基础世界地图、时间、事件系统
- ✅ 多样化地形类型(平原、山脉、森林、沙漠、水域等)
- ✅ 基于Web前端显示界面
- ✅ 基础模拟器框架
- ✅ 配置文件
- ✅ release 一键即玩的exe
- ✅ 菜单栏 & 存档 & 读档
- ✅ 灵活自定义LLM接口
- ✅ 支持mac os
- ✅ 多语言本地化
- ✅ 开始游戏页
- ✅ BGM & 音效
- [ ] Mod支持
- ✅ 基础tile地块系统
- ✅ 基础区域、修行区域、城市区域、宗门区域
- ✅ 同地块NPC交互
- ✅ 灵气分布与产出设计
- ✅ 世界事件
- ✅ 角色基础属性系统
- ✅ 修炼境界体系
- ✅ 灵根系统
- ✅ 基础移动动作
- ✅ 角色特质与性格
- ✅ 境界突破机制
- ✅ 角色间的相互关系
- ✅ 角色交互范围
- ✅ 角色Effects系统:增益/减益效果
- ✅ 角色功法
- ✅ 角色兵器 & 辅助装备
- ✅ 丹药
- ✅ 角色长短期记忆
- ✅ 角色的长短期目标,支持玩家主动设定
- ✅ 角色绰号
- [ ] 生活技能
- ✅ 铸造
- ✅ 炼丹
- [ ] 种植
- [ ] 饲养
- [ ] 技能可升级
- ✅ 凡人系统
- [ ] 宗门系统
- ✅ 设定、功法、疗伤、驻地、行事风格
- ✅ 宗门特殊动作:合欢宗(双修),百兽宗(御兽)
- ✅ 宗门等阶
- [ ] 宗门意志ai
- [ ] 宗门任务
- [ ] 世家系统
- [ ] 朝廷系统(未定)
- [ ] 组织间关系网络
- ✅ 基础移动动作
- ✅ 动作执行框架
- ✅ 有明确规则的定义动作
- ✅ 长动作执行和结算系统
- ✅ 支持多月份持续的动作(如修炼、突破、游戏等)
- ✅ 动作完成时的自动结算机制
- ✅ 多人动作:动作发起与动作响应
- ✅ 影响人际关系的LLM动作
- ✅ 系统性的动作注册与运行逻辑
- ✅ 天地灵气变动
- ✅ 多人大事件:
- ✅ 拍卖会
- ✅ 秘境探索
- [ ] 比武大会
- [ ] 宗门大比
- [ ] 突发事件
- [ ] 宝物/洞府出世
- [ ] 自然事件:
- [ ] 自然灾害
- [ ] 兽潮
- ✅ 优劣互克关系
- ✅ 胜率计算系统
- ✅ 基础物品、灵石框架
- ✅ 物品交易机制
- ✅ 动植物
- ✅ 狩猎、采集、材料系统
- [ ] 魔兽
- ✅ LLM接口集成
- ✅ 角色AI系统(规则AI + LLM AI)
- ✅ 协程化决策机制,异步运行,多线程加速ai决策
- ✅ 长期规划和目标导向行为
- ✅ 突发动作响应系统(对外界刺激的即时反应)
- ✅ LLM驱动的NPC对话、思考、互动
- ✅ LLM生成小片段剧情
- ✅ 根据任务需求分别接入max/flash模型
- ✅ 小剧场
- ✅ 战斗小剧场
- ✅ 对话小剧场
- ✅ 小剧场不同文字风格
- ✅ 一次性选择(如是否要切换功法)
- ✅ 注入基础世界知识
- ✅ 用户输入历史,动态生成功法、装备、宗门、区域信息
- ✅ 奇遇
- ✅ 天劫 & 心魔
- [ ] 夺舍 & 重生
- [ ] 机缘 & 因果
- [ ] 占卜 & 谶纬
- [ ] 男生女相 & 女生男相
- [ ] 角色隐秘 & 双面人
- [ ] 飞升上界
- [ ] 阵法
- [ ] 阴谋
- [ ] 世界秘密 & 世界法则
- [ ] 炼蛊
- [ ] 灭世危机
- [ ] 历史/事件的小说化&图片化&视频化
- [ ] MCP agent化,修士自行调用工具
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for cultivation-world-simulator
Similar Open Source Tools
cultivation-world-simulator
Cultivation World Simulator is an AI-driven open-world cultivation simulator where players take on the role of 'Tian Dao' (God) to observe and influence the world of cultivators. The simulator features AI-driven NPCs with unique personalities, memories, and behaviors, a detailed world system based on cultivation elements like spiritual roots and techniques, emergent storytelling without predefined scripts, and a focus on creating a truly immersive cultivation world experience.
KubeDoor
KubeDoor is a microservice resource management platform developed using Python and Vue, based on K8S admission control mechanism. It supports unified remote storage, monitoring, alerting, notification, and display for multiple K8S clusters. The platform focuses on resource analysis and control during daily peak hours of microservices, ensuring consistency between resource request rate and actual usage rate.
AstrBot
AstrBot is an open-source one-stop Agentic chatbot platform and development framework. It supports large model conversations, multiple messaging platforms, Agent capabilities, plugin extensions, and WebUI for visual configuration and management of the chatbot.
aituber-kit
AITuber-Kit is a tool that enables users to interact with AI characters, conduct AITuber live streams, and engage in external integration modes. Users can easily converse with AI characters using various LLM APIs, stream on YouTube with AI character reactions, and send messages to server apps via WebSocket. The tool provides settings for API keys, character configurations, voice synthesis engines, and more. It supports multiple languages and allows customization of VRM models and background images. AITuber-Kit follows the MIT license and offers guidelines for adding new languages to the project.
NGCBot
NGCBot is a WeChat bot based on the HOOK mechanism, supporting scheduled push of security news from FreeBuf, Xianzhi, Anquanke, and Qianxin Attack and Defense Community, KFC copywriting, filing query, phone number attribution query, WHOIS information query, constellation query, weather query, fishing calendar, Weibei threat intelligence query, beautiful videos, beautiful pictures, and help menu. It supports point functions, automatic pulling of people, ad detection, automatic mass sending, Ai replies, rich customization, and easy for beginners to use. The project is open-source and periodically maintained, with additional features such as Ai (Gpt, Xinghuo, Qianfan), keyword invitation to groups, automatic mass sending, and group welcome messages.
prompt-optimizer
Prompt Optimizer is a powerful AI prompt optimization tool that helps you write better AI prompts, improving AI output quality. It supports both web application and Chrome extension usage. The tool features intelligent optimization for prompt words, real-time testing to compare before and after optimization, integration with multiple mainstream AI models, client-side processing for security, encrypted local storage for data privacy, responsive design for user experience, and more.
PersonalExam
PersonalExam is a personalized question generation system based on LLM and knowledge graph collaboration. It utilizes the BKT algorithm, RAG engine, and OpenPangu model to achieve personalized intelligent question generation and recommendation. The system features adaptive question recommendation, fine-grained knowledge tracking, AI answer evaluation, student profiling, visual reports, interactive knowledge graph, user management, and system monitoring.
gzm-design
Gzm Design is a free and open-source poster designer developed using the latest mainstream technologies such as Vue3, Vite4, TypeScript, etc. It provides features like PSD import, JSON import, multiple pages support, shortcut key support, template import, layer management, ruler tool, pen tool, element editing, preview, file download, canvas zooming and dragging, border stroke, filling, blending modes, text formatting, group handling, canvas size modification, rich text support, masking, shadow effects, undo/redo functionality, QR code tool, barcode tool, and ruler line npm package encapsulation.
all-in-rag
All-in-RAG is a comprehensive repository for all things related to Randomized Algorithms and Graphs. It provides a wide range of resources, including implementations of various randomized algorithms, graph data structures, and visualization tools. The repository aims to serve as a one-stop solution for researchers, students, and enthusiasts interested in exploring the intersection of randomized algorithms and graph theory. Whether you are looking to study theoretical concepts, implement algorithms in practice, or visualize graph structures, All-in-RAG has got you covered.
build_MiniLLM_from_scratch
This repository aims to build a low-parameter LLM model through pretraining, fine-tuning, model rewarding, and reinforcement learning stages to create a chat model capable of simple conversation tasks. It features using the bert4torch training framework, seamless integration with transformers package for inference, optimized file reading during training to reduce memory usage, providing complete training logs for reproducibility, and the ability to customize robot attributes. The chat model supports multi-turn conversations. The trained model currently only supports basic chat functionality due to limitations in corpus size, model scale, SFT corpus size, and quality.
Chenyme-AAVT
Chenyme-AAVT is a user-friendly tool that provides automatic video and audio recognition and translation. It leverages the capabilities of Whisper, a powerful speech recognition model, to accurately identify speech in videos and audios. The recognized speech is then translated using ChatGPT or KIMI, ensuring high-quality translations. With Chenyme-AAVT, you can quickly generate字幕 files and merge them with the original video, making video translation a breeze. The tool supports various languages, allowing you to translate videos and audios into your desired language. Additionally, Chenyme-AAVT offers features such as VAD (Voice Activity Detection) to enhance recognition accuracy, GPU acceleration for faster processing, and support for multiple字幕 formats. Whether you're a content creator, translator, or anyone looking to make video translation more efficient, Chenyme-AAVT is an invaluable tool.
godoos
GodoOS is an efficient intranet office operating system that includes various office tools such as word/excel/ppt/pdf/internal chat/whiteboard/mind map, with native file storage support. The platform interface mimics the Windows style, making it easy to operate while maintaining low resource consumption and high performance. It automatically connects to intranet users without registration, enabling instant communication and file sharing. The flexible and highly configurable app store allows for unlimited expansion.
Con-Nav-Item
Con-Nav-Item is a modern personal navigation system designed for digital workers. It is not just a link bookmark but also an all-in-one workspace integrated with AI smart generation, multi-device synchronization, card-based management, and deep browser integration.
KouriChat
KouriChat is a project that seamlessly integrates virtual and real interactions, providing eternal gentle bonds. It offers features like WeChat integration, immersive role-playing, intelligent conversation segmentation, emotion-based emojis, image generation, image recognition, voice messages, and more. The project is focused on technical research and learning exchanges, with a strong emphasis on ethical and legal guidelines. Users are required to take full responsibility for their actions, especially minors who should use the tool under supervision. The project architecture includes avatar configurations, data storage, handlers, AI service interfaces, a web UI, and utility libraries.
get_jobs
Get Jobs is a tool designed to help users find and apply for job positions on various recruitment platforms in China. It features AI job matching, automatic cover letter generation, multi-platform job application, automated filtering of inactive HR and headhunter positions, real-time WeChat message notifications, blacklisted company updates, driver adaptation for Win11, centralized configuration, long-lasting cookie login, XPathHelper plugin, global logging, and more. The tool supports platforms like Boss直聘, 猎聘, 拉勾, 51job, and 智联招聘. Users can configure the tool for customized job searches and applications.
For similar tasks
cultivation-world-simulator
Cultivation World Simulator is an AI-driven open-world cultivation simulator where players take on the role of 'Tian Dao' (God) to observe and influence the world of cultivators. The simulator features AI-driven NPCs with unique personalities, memories, and behaviors, a detailed world system based on cultivation elements like spiritual roots and techniques, emergent storytelling without predefined scripts, and a focus on creating a truly immersive cultivation world experience.
MinePal
MinePal is a Minecraft companion app with a React frontend, a local backend, and an AI agent. The frontend is built with React and Vite, the local backend APIs are in server.js, and the Minecraft agent logic is in src/agent/. Users can set up the frontend by installing dependencies and building it, refer to the backend repository for backend setup, and navigate to src/agent/ to access actions that the bot can take.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.












