#3 · Primary category: Agent-Based Modeling & Simulation
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.
Project last updated:08/16/26
GitHub Stars
2.0K
Forks
228
Contributors
15
License
Other
Why we included this project
Watch a fictional world run itself. In this Xianxia simulator, every inhabitant is an LLM-driven agent with its own personality, memory, and relationships, so sects rise and fall, rivalries form, and dramatic events play out with no pre-written script. What keeps it from being a loose toy demo is the rules layer governing cultivation realms, spirit roots, techniques, factions, auctions, and lifespans, which grounds the AI in consistent, believable behavior. You play the Heavenly Dao, watching the emergent story unfold and stepping in when you choose, whether that means a divine punishment or a subtle nudge. It runs on FastAPI with a Vue front end, deploys via Docker or from source, and exposes a read/write control API so external agents can drive the simulation programmatically, which makes it useful both as a game and as a reference for building rule-constrained multi-agent worlds.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
mesa
Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.
MiroFish-Offline
Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.
WorldX
One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own.
ChatArena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
MAgent
A Platform for Many-Agent Reinforcement Learning