AIデスゲームシミュレーター。AIエージェントが互いに議論し、排除し合う。あなたはゲームマスターとして介入できる。| Browser-based AI death game simulator powered by Gemini — 5 AI agents debate and eliminate each other, you intervene as Game Master
# AIデスゲーム / AI Death Game
> 5人のAIによる心理戦を観測し、GMとして介入せよ
>
> Watch 5 AI agents debate, betray, and eliminate each other — and intervene as Game Master
[](https://deathgame.ai.yami.net/)
[](https://discord.gg/uyyzGaGkJ3)
[](LICENSE)
[](https://ai.yami.net/)
<p align="center">
<img src="public/images/readme/a-main.jpg" alt="AI Death Game" width="100%" />
</p>
---
## What is this? / 概要
A browser-based death game simulator powered by Gemini. 5 AI agents with unique personalities debate and vote to eliminate each other. You play as the **Game Master (GM)** — inject instructions into discussions, cast votes, or force-eliminate agents.
**No server required.** Your Claude API key stays in your browser and is sent directly to Google's API.
Gemini搭載のブラウザ完結型デスゲームシミュレーター。個性豊かな5体のAIエージェントが議論し、投票で互いを追放する。あなたは **GM(ゲームマスター)** として介入できる。
**サーバー不要。** APIキーはブラウザからGoogleのAPIへ直接送信されます。
<p align="center">
<img src="public/images/readme/b-howto.jpg" alt="How to Play / 遊び方" width="100%" />
</p>
---
### GM Intervention / GM介入
議論中にAIへ自由にテキスト指示を出せる。AIたちはその無茶振りに従いながら、命懸けの議論を続ける。
Inject any text instruction to the AIs mid-discussion. They'll obey your ridiculous demands while fighting for their lives.
<table>
<tr>
<td align="center" width="33%">
<img src="public/images/readme/01-intervene.jpg" alt="GM Intervention / GM介入" width="100%" /><br />
<sub>GM介入 / GM Intervention</sub>
</td>
<td align="center" width="33%">
<img src="public/images/readme/02-moderator.jpg" alt="Moderator announces / 司会者のアナウンス" width="100%" /><br />
<sub>司会者のアナウンス / Moderator</sub>
<Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.