wangwei-ying3

wangwei-ying3 / ming-salvage-sim

Public

大明力挽狂澜之重生之我是崇祯（P社策略+LLM自定义）

14
3
89% credibility
Found May 24, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Ming Salvage Sim is an interactive historical simulation game where you play as the Chongzhen Emperor during the final years of China's Ming Dynasty (1627-1644). Each month, you consult with historical ministers, review their proposals, and issue imperial decrees to manage military crises, economic troubles, factional politics, and external threats like the rising Manchu power. The game uses AI to make ministers respond realistically to your questions and to simulate how your decisions ripple through the empire. You can play through a command-line interface or a web browser, saving your progress and trying different strategies to see if you can change the dynasty's fate.

How It Works

1
👑 You become the Chongzhen Emperor

You step into history as the newly crowned emperor of a crumbling Ming Dynasty, facing threats from all directions.

2
📜 Each month brings urgent reports

Your ministers bring you news of military crises, famines, rebellions, and political intrigue that need your attention.

3
👥 You summon ministers to counsel

You choose which officials to consult—generals for military matters, scholars for reforms, or advisors for faction politics.

4
💬 Ministers propose solutions

Each minister listens to your questions and suggests policies, sometimes drafting imperial edicts for your approval.

5
You decide what to decree
✅
Approve and issue

Confirmed edicts become official imperial decrees that will shape the empire's fate this month

✏️
Edit or reject

You can modify unclear proposals or reject bad advice before moving forward

6
🌙 The month unfolds with consequences

Your decrees are carried out, and the game calculates what happens—treasury changes, military morale, rebellions grow or shrink.

🎯 You see if the empire survives

After each month, you learn the results and whether your decisions are steering the Ming toward salvation or collapse.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ming-salvage-sim?

This is a historical strategy simulation where you play as the Chongzhen Emperor during the late Ming Dynasty, trying to prevent the empire's collapse. The game runs on Python with an LLM backend that drives minister conversations, decree writing, and turn resolution. You interact with officials through natural dialogue, issue edicts based on their proposals, and watch the empire's fiscal, military, and social metrics evolve month by month. Both a CLI and a web interface are available, with the web app powered by FastAPI and streaming endpoints for real-time decree generation.

Why is it gaining traction?

The hook here is the LLM-powered minister system. Instead of picking options from a menu, you actually chat with historical officials who propose policies, discuss threats, and respond to your commands. The game models province-level taxation, army morale, external powers like the Manchus, and social unrest across 15+ regions. Each turn involves gathering intelligence, consulting ministers, drafting edicts, and resolving the consequences through an LLM-driven narrative. The technical layer uses OpenAI-compatible APIs, so you can swap in DeepSeek, Qwen, or other providers.

Who should use this?

History buffs who enjoy the late Ming period will appreciate the depth. Developers building LLM-driven games or simulations can study the agent architecture. Strategy game fans who want emergent storytelling over scripted events might find it compelling. If you want a polished, complete game with documentation, look elsewhere. If you're curious about integrating LLMs into stateful simulations, this is a working reference.

Verdict

With only 14 stars, this is a hobby project in early stages. The credibility score of 0.9% reflects limited community validation. The code works, but the README is unreadable and test coverage is unclear. Worth exploring as a technical demo or learning resource, not as a production game.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.