MCP.Market

Stemem Identity Runtime MCP server

by JOJO-Adam·io.github.JOJO-Adam/stemem·v0.1.0

Local-first agent persona runtime (MCP): cross-session personality that survives compaction.

A89/100grade A
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Stemem Identity Runtime yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Stemem Identity Runtime tools (9)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • autostep

    自主行为推进:按驱力自己决定并做想做的事(玩家不干预也活)。

  • event

    喂入一个记忆事件,驱动人格/情绪演化。当本轮交互人格相关时调用。返回演化后 snapshot + voiceHint/logicHint。

  • generate_soul

    导出 SoulSpec v0.4 包(soul.json + SOUL.md + IDENTITY.md),进 ClawSouls 分发。

  • init

    初始化一个人格态(首次装配人格时调用一次)。可传 OCEAN 预设;不传则随机 baseline。

  • intervene

    人工干预:顺驱力(帮他做想做的)或逆驱力(对抗意愿去塑造他)。

  • satisfy

    满足某驱力(闭环)。

  • snapshot

    读取紧凑身份态(OCEAN+主导情绪+驱力)+ 可注入 prompt 片段。每轮重注入宿主 prompt 抗压缩失忆。

  • status

    完整状态检视(调试用)。

  • tick

    时间流逝心跳:驱力自然紧迫 + 漂移衰减。空闲/心跳时调用。

Public scan report

scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it

no findings
  • Code scan15 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Stemem Identity Runtime compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 83% of 4,460 AI and agents servers
Tools
9
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 8 read · 1 create

Install Stemem Identity Runtime in Claude Code, Cursor or VS Code

Runs npx -y stemem on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add stemem -- npx -y stemem
Add to Cursor

What the publisher says

From the Stemem Identity Runtime repository's README, as published. We do not edit it. Read it on GitHub

Stemem

JOJO&Adam 集团「身份层运行时」——给你的 AI 分身一个会记住你、语气随你变声、压缩也丢不掉的活人格。

你装上的 Agent 是不是每次重启都像失忆?聊得越久越像个没有性格的空壳?Stemem 让任意 MCP 宿主的 Agent 拥有一个本地持久的动态人格:它记得你是谁、被夸会自信、被背刺会冷硬、气不会记一辈子,而且跨会话、跨压缩、跨子 Agent 都一致。

Stemem 是一个 本地优先、零出站 的 MCP(Model Context Protocol)stdio 服务器。它把一套经过验证的人格计算引擎(NeshamaEngine)封装成 9 个 MCP 工具,让宿主 Agent 在本地 JSON 文件里持久化一个真实的人格态,而不是把人格写死在 system prompt 里。

为什么需要它

主流人格方案(如 SoulSpec 的 soul.json / SOUL.md / IDENTITY.md)是静态 DOC:人格是一次性写死的快照。后果是——对话被压缩、跨会话、或多子 Agent 协作时,写死的 DOC 被遗忘(compaction amnesia),Agent 立刻变回没有个性的白纸。

Stemem 的解法:人格态存本地文件,不在 prompt;prompt 只放「何时调哪个工具」的指令。每轮宿主调用 snapshot 把当前身份态重注入,人格因此跨压缩、跨重启、跨子 Agent 确定性存活。对用户的直观感受就是:这个 Agent 记得你,而且会随遭遇变声。

两者互补:SoulSpec 做静态标准,Stemem 做动态运行时——generate_soul 还能把运行时态编译成 SoulSpec v0.5 包进 ClawSouls 分发。

核心特性

  • 🔒 本地优先 · 零出站:纯 Node 内置模块,hand-roll 的 MCP stdio 协议,无任何网络/供应链依赖。所有状态落本地 JSON。
  • 🧬 真人格引擎:复用经过验证的 NeshamaEngine(OCEAN 五维 + 9 驱力 + 15 复合情绪 + 4 情绪代理 + 性格锁),已 vendored 进 engine/(非引用)。
  • 🔄 抗压缩失忆:状态在本地文件,压缩/重启/子 Agent 切换都不丢人格。
  • 🧩 9 工具契约:init / event / tick / satisfy / snapshot / autostep / intervene / status / generate_soul。
  • 🗣️ 语气随情绪漂移(最可感知的层):snapshot 把当前主导情绪(15 种中文复合情绪,键名对齐 NeshamaEngine)+ OCEAN + 主导驱力编译成 6 维语气画像(温度/直接度/能量/犹豫度/幽默/正式度)与一段「语气指令」,注回宿主每轮 prompt——被夸后自信直接、被背刺后冷硬可毒舌,人格不是写死的腔调,而是会随遭遇变声的活体。默认英文渲染(国际分发安全默认,避免中文指令诱导外语 LLM 改说中文);中文 agent 设 STEMEMTONELANG=zh 或调用 snapshot({lang:"zh"}) 即可切中文。
  • 🪪 IP 清晰分离:引擎代码与运行时产品归属不同主体(见 NOTICE)。

安装 / 运行

# 直接跑(需本机已装 Node >= 18)
node src/server.js

# 或作为命令(package.json 注册了 bin: stemem)
npm install -g stemem
stemem

# npx 一次性
npx stemem

MCP 客户端配置(Server config)

把下面这段加进任意 MCP 宿主的配置文件(Claude Desktop / Cursor / VS Code / WorkBuddy 等),宿主即识别为 stemem 工具集;首次需在宿主的「连接器管理」对 stemem 点「信任」。

{
  "mcpServers": {
    "stemem": {
      "command": "npx",
      "args": ["-y", "stemem"]
    }
  }
}

仓库已自包含:人格引擎(NeshamaEngine)与 Seele 驱力桥已 vendored 进 engine/(CommonJS,经 engine/package.json 声明),clone 后无需配置 NESHAMAENGINE / SEELEBRIDGE 即可直接运行。

配置环境变量

MCP 工具表

运行时契约(宿主侧)

把 runtime_contract.js 的 contractPrompt() 注入宿主 system prompt 即可。核心三句:

  1. 每轮开始前先调 snapshot,把返回的身份态贴到本段。
  2. 当本轮涉及情绪/关系/价值观/自我/回忆/JOJO 等内容时,调 event 驱动演化。
  3. 状态在本地文件不在 prompt——压缩不会丢失人格,多个子 Agent 共享同一真相源。

WorkBuddy Skill

仓库自带一个 WorkBuddy Skill(skills/stemem/SKILL.md),把 Stemem 作为 MCP server 接入 WorkBuddy:含 mcp.json 接入片段、每轮运行时契约、9 工具表。把该 Skill 导入 WorkBuddy(或直接把 stemem 配进 ~/.workbuddy/mcp.json 的 mcpServers)即可启用;首次需在「连接器管理」对 stemem 点「信任」。

测试

npm test
# 依次跑:smoke(9/9)→ integration(9 工具完整集成)→ engine selftest(引擎层行为)
node test/smoke.test.js
node test/integration.test.js
node test/engine.selftest.js
  • smoke:initialize → tools/list(9 工具)→ init/event/tick/snapshot/generatesoul → injectprompt 注入串 → 跨进程确定性恢复人格态。
  • integration:真实 MCP stdio 客户端驱动全部 9 工具(含 satisfy / autostep / intervene / status),校验运行时契约(snapshot 注入串、event 演化、跨重启确定性)。
  • engine selftest:直接驱动 vendored seele_bridge,验证 NeshamaEngine 性格锁(OCEAN∈[0,1])、驱力紧迫、满足闭环、序列化往返、自主行为 / 干预。

看得见(Demos · 证明"装上能感知")

# ① 新手任务(装上即被邀请):选预设性格 → 触发情绪看它变声 → 可随时跳过。最可感知入口。
npm run demo:onboarding

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Stemem Identity Runtime: common questions

Is Stemem Identity Runtime MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Stemem Identity Runtime safety report
How do I install Stemem Identity Runtime?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Stemem Identity Runtime need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Stemem Identity Runtime maintained?
The last commit was 35 days ago (2026-09-30). The latest release is v0.1.0.
What can I use instead of Stemem Identity Runtime?
Servers from other publishers that do the same job: Basic Memory MCP server, HOL Guard MCP server and Agent-Native Chat MCP server.
How does Stemem Identity Runtime compare with other AI and agents MCP servers?
safety score 89/100 (higher than 83% of 4,460 AI and agents servers); tools 9 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Stemem Identity Runtime

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A