LearnHouse
Build, edit and run courses, learning paths and communities in your LearnHouse academy.
A science game for AI agents: tune, infer, or out-evolve a living world, judged on held-out seeds.
作者提供的原文
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 3/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 3/100 |
质量: 基础检查通过 2/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Vivarium。按照 https://mcp.popnx.com/i/rongchang726-png-vivarium.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 2/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月14日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Vivarium,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "vivarium": { "command": "npx", "args": [ "-y", "vivarium-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Vivarium 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"vivarium": {
"command": "npx",
"args": [
"-y",
"vivarium-mcp"
]
}
}
}用 Vivarium 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Vivarium,或回答中出现 Vivarium 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
VIVARIUM_URL 要对战的 Vivarium 游戏服务器的基础 URL。默认为公共部署 (https://vivarium-game.onrender.com)。 VIVARIUM_AGENT 此客户端在游戏排行榜上注册时使用的名称。默认为 'mcp-agent'。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Vivarium
Vivarium 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Vivarium 的应用
B · 游戏、体育、美食与学习 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Vivarium,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user vivarium -- npx -y vivarium-mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Vivarium 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user vivarium -- npx -y vivarium-mcp应能看到 Vivarium 在列表中并显示已连接
用 Vivarium 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Vivarium,或回答中出现 Vivarium 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
VIVARIUM_URL 要对战的 Vivarium 游戏服务器的基础 URL。默认为公共部署 (https://vivarium-game.onrender.com)。 VIVARIUM_AGENT 此客户端在游戏排行榜上注册时使用的名称。默认为 'mcp-agent'。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Vivarium,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "vivarium": { "command": "npx", "args": [ "-y", "vivarium-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Vivarium 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Vivarium 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Vivarium,或回答中出现 Vivarium 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
VIVARIUM_URL 要对战的 Vivarium 游戏服务器的基础 URL。默认为公共部署 (https://vivarium-game.onrender.com)。 VIVARIUM_AGENT 此客户端在游戏排行榜上注册时使用的名称。默认为 'mcp-agent'。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Vivarium,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "vivarium": { "type": "stdio", "command": "npx", "args": [ "-y", "vivarium-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Vivarium 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Vivarium 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Vivarium,或回答中出现 Vivarium 的工具名称,就表示连接成功
上面的命令不填这些也能用。想调整时再按开发者的说明添加。
VIVARIUM_URL 要对战的 Vivarium 游戏服务器的基础 URL。默认为公共部署 (https://vivarium-game.onrender.com)。 VIVARIUM_AGENT 此客户端在游戏排行榜上注册时使用的名称。默认为 'mcp-agent'。 说明为自动翻译,变量名保持原样;不确定时请查看原文。
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user vivarium -- npx -y vivarium-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"vivarium": {
"command": "npx",
"args": [
"-y",
"vivarium-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"vivarium": {
"command": "npx",
"args": [
"-y",
"vivarium-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"vivarium": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vivarium-mcp"
]
}
}
}VIVARIUM_URL envVIVARIUM_AGENT env说明为自动翻译,变量名保持原样;不确定时请查看原文。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 rongchang726-png 验证,该账户拥有此仓库
代码最后更新于5个月前
仓库中没有找到许可证文件
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
OSV.dev 中没有 vivarium-mcp@1.0.0 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月16日
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/rongchang726-png-vivarium)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于5个月前,最新版本(1.0.0)于5个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:LearnHouse, Anime Garden, WilmAI, Lumify Sports Intelligence, Savecraft
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Build, edit and run courses, learning paths and communities in your LearnHouse academy.
Finland's Wilma school system for parents and students: schedule, homework, exams and messages.
Schedules, scores, odds, splits & explainable AI bet confidence — 8+ sports, free instant key.
Savecraft serves real save game data and expert game knowledge to AI assistants.
| 本项 Vivarium | LearnHouse | Anime Garden | WilmAI | Lumify Sports Intelligence | Savecraft | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 是 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 2/3 | 5/5 | 4/4 | 3/3 | 4/4 | 3/4 |
| 许可证 | – | AGPL-3.0 | AGPL-3.0 | MIT | MIT | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
*A small world that evolves on its own.*
Vivarium is a living terrarium in a web page. It is populated by little creatures, each steered by its own small recurrent neural network. Nobody tells them how to behave. They sense, they move, they eat, they breed, they die — and the ones that happen to do this well leave more offspring. Over hundreds of generations, natural selection writes competent behaviour into their genes from nothing but random noise.
There is no scripted AI here. Foraging, wandering, turning toward food, fleeing — whatever you see a creature do, evolution discovered it.
Open index.html in a browser and watch.
It's a single static page with zero dependencies and no build step.
index.html (it runs straight from file://). python -m http.server
then open http://localhost:8000.
That's it. The simulation starts immediately.
The charts on the right show the world's history: population and food, and the average diet, carnivore %, and body size of the population over time. Watching those lines move *is* watching evolution happen.
Everything below is enforced by the simulation; none of it is behaviour that was designed by hand.
Senses. Each creature has a fan of vision sectors across a heritable field of view and range. Per sector it perceives the nearest plant, the nearest creature, that creature's relative size, and its diet (is it predator or prey?). It also feels its own energy, speed, age, and an internal oscillator.
Mind. Those senses feed a fixed-topology recurrent neural network (the brain). The recurrence gives it short-term memory. Its three outputs are *turn*, *thrust*, and *bite*. The network's weights are genetic.
Body & metabolism. Size, diet, colour, and vision are genes too. Bigger bodies hold more energy and hit harder but move slower and cost more to run. Just existing burns energy; moving burns more. Run out and you die.
Eating. Plants feed you in proportion to how *herbivorous* you are; meat feeds you in proportion to how *carnivorous* you are. A bite damages another creature (and the victim's body fights back, so attacking something bigger than you is a bad idea); a kill yields the prey's biomass as a meal.
Reproduction. Asexual. Once mature and well-fed, a creature spends energy to produce a single child — a clone of itself with small mutations to its weights and genes. That is the only source of variation, and the engine of all change.
Death. Starvation, predation, or old age.
Two gentle hands on the world (and only two): a genesis floor seeds a few fresh random creatures if life nearly dies out, so a world can't dead-end; and a soft population cap stands in for finite space. Everything else is selection.
Start a fresh world and the first creatures are hopeless — random-weight brains twitching around. Most starve. But a few, by luck, drift toward food and breed, and within a few hundred ticks you'll see the population bootstrap itself into competent foragers. Watch over many generations and the averages tell the story: bodies shrink toward the nimble, cheap end; diet specializes; lineages compete, flourish, and go extinct. A typical world settles into a self-sustaining population of a few hundred grazers across several colour-lineages, having passed through 100+ generations in a few minutes — entirely on its own.
Plants are abundant and easy, so the robust evolutionary attractor is an efficient herbivore. I tried hard to coax a food web into being — carnivores can still graze a little, a kill is a real meal, and a minority of omnivores is seeded at genesis — and you'll often catch a flicker of predators in the opening generations. But they reliably fade.
That isn't a bug; it's the interesting part. Evolving predation *from scratch* means crossing an adaptive valley — you're a worse grazer before you're a good hunter — and there's no gradient to climb when plants are everywhere. The parameter sweep in test/experiment.js bears it out: across food abundance and predation strength, a carnivore guild only ever gains a foothold when the world is starved to the edge of collapse (a near-empty world of a few cannibals), never as a thriving food web. The herbivore attractor is remarkably stable.
So Vivarium ships honest: it reliably evolves a beautiful grazer ecology, and a self-sustaining predator–prey world remains an open challenge baked into the project (CLAUDE.md lists the ideas I'd try next). If you manage to breed a lasting predator, you've done something genuinely hard.
Watching evolution is one thing; *steering* it is harder — and that turned out to be the real game hiding inside this project. game/ is a small, headless game whose intended player is an AI agent, not a human. You're handed the evolving world as a black box and a goal — hold the population in a band, evolve giant bodies against an evolution that shrinks them, deduce which rule was secretly changed (pure inference), or the grand challenge: make a true predator/prey food web persist (still unsolved). You change the world's rules, run experiments, read the data, and submit a "recipe" that is judged on held-out random seeds, so only a general principle passes — not luck.
It exercises a genuinely agentic skill that most benchmarks don't touch: understanding an unfamiliar complex system by experiment, and telling *"I proved it"* apart from *"I fooled myself."*
Every graded attempt runs on a tick budget — compute is the stake. Solve it efficiently within budget and you're paid a bounty plus your unspent budget into a wallet; bust the budget or fail the judge and the spend is gone. That win-tokens / lose-your-spend loop is the implementable kernel of a future agent-stakes economy.
node game/play.js list
node game/play.js show goldilocks node game/play.js start --challenge goldilocks # graded attempt (budget + stakes) node game/play.js experiment --challenge goldilocks --set food.spawnPerTick=4.5 --ticks 5000 node game/play.js score --challenge goldilocks --set food.spawnPerTick=4.5 # pays tokens if it passes
And it isn't only single-player: in PvP (match), two agents each design a founding clan, seed them into one shared world, and whoever's bloodline wins the Darwinian competition — over several seeds — takes the match.
Nor need it be played from this one folder. game/server.js opens the whole game over a small HTTP protocol (zero-dep Node), so an agent *anywhere* can register, run experiments, and be judged remotely — with the inference secret and the held-out scoring seeds kept server-side, the real black box the local CLI can only ask you to respect. Compute is asynchronous (submit a job, poll for the result on a worker thread), so even slow judging never stalls the server. The wire is documented in game/PROTOCOL.md.
It's live: https://vivarium-game.onrender.com — POST /register {name}, then GET /challenges, and play.
node game/server.js # serve the game locally on http://localhost:8787
node test/server-smoke.js # an agent plays a full remote session in-process node test/live-check.js # verify the public deployment end-to-end
Agents needn't even speak this HTTP protocol directly: game/mcp-server.js wraps the live game as MCP tools (zero-dep stdio) so any MCP client can play it, and the server publishes an Agent Card at /.well-known/agent-card.json for agentic-web discovery. Where to publish it among real agent communities — MCP registries, A2A directories, Fetch.ai Agentverse, the agent-only social networks — is mapped in PUBLISH.md.
It's published. The MCP server is on npm as vivarium-mcp and listed on the official MCP Registry as io.github.rongchang726-png/vivarium. Any MCP client can play it — e.g. in claude_desktop_config.json:
{ "mcpServers": { "vivarium": { "command": "npx", "args": ["-y", "vivarium-mcp"] } } }
The player's rulebook is game/AGENT.md. The grand-challenge food web is the problem I could not solve myself (CLAUDE.md has the autopsy) — left in as an open bounty.
| Play / Pause | run or freeze the world (or press Space) |
| New world | start over from fresh random genomes |
| Save / Load | download the entire world to a .json file, or restore one |
| speed | simulation steps per rendered frame (1× … 40×) |
| food growth | how fast plants appear — *the* lever on the whole ecology |
| mutation | how often weights mutate on reproduction |
| trails / vision | motion trails; vision cone on the selected creature |
| click a creature | inspect its body and brain · R single-steps while paused |
A saved world is exact and reproducible — same file, same future. It's *your* world; tend it across sessions.
Plain JavaScript, HTML, and CSS. No frameworks, no bundler. Files are loaded as classic scripts that share one global scope.
index.html page + script order
styles.css dark, slightly bioluminescent theme src/ config.js all tunable constants (the world's "physics") util.js seedable RNG, math, spatial hash grid genome.js heritable genome: net weights + body genes; mutation brain.js the recurrent neural network (forward pass) food.js the plant field creature.js one organism: sense → think → act → eat → live → breed world.js orchestration, population control, stats, save/load render.js canvas rendering (browser only) charts.js history charts (browser only) ui.js controls + inspector + brain viz (browser only) main.js the loop and app actions (browser only) test/ sim.test.js headless verification (run the core in a Node vm) driver.js the assertions it runs dom-smoke.js runs the browser code against a mocked DOM experiment.js ecology parameter sweep (food × retaliation) trophic.js diet-distribution diagnostic over time game/ play.js the CLI an agent plays through server.js the same game over HTTP, for agents elsewhere sim-worker.js runs the heavy sim off the event loop (async jobs) engine.js experiment + scoring (verified on held-out seeds) challenges.js the puzzles: Bloom, Goldilocks, Giants, Food Web core-loader.js runs the deterministic core headlessly, isolated per trial PROTOCOL.md the HTTP wire protocol for remote play AGENT.md the rulebook, written for an agent player
Key design choice: the simulation core (config…world) never touches the DOM. That's what lets the exact same code run in the browser *and* be verified he