← 返回 Skills 市场
huamu668

MemOS Cloud Integration

作者 huamu668 · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
411
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install huamu668-memos-cloud
功能描述
Recall memories from MemOS Cloud before responding. Use this skill when you need context about user's previous conversations, preferences, or decisions.
使用说明 (SKILL.md)

MemOS 记忆召回

在回答前从 MemOS Cloud 召回相关记忆。

使用方式

当需要上下文时,执行以下命令:

node ~/.claude/plugins/memos-cloud/memos-api.js search "{user_query}"

参数

  • user_query - 用户的输入或提炼的搜索关键词

处理结果

成功返回记忆

将记忆整合到回复中:

根据之前的记录,{memory_content}

无相关记忆

正常回复,不提及记忆功能。

API 错误

静默失败,正常回复。

示例场景

用户: "我之前说的那个项目怎么样了?" 动作:

node ~/.claude/plugins/memos-cloud/memos-api.js search "之前说的那个项目"

回复: "根据之前的记录,你提到的项目是 X,当时..."


用户: "我还是喜欢之前那个方案" 动作:

node ~/.claude/plugins/memos-cloud/memos-api.js search "方案偏好"

回复: "根据记录,你之前倾向于..."

安全使用建议
The skill appears to intend contacting MemOS Cloud via a local Node script and an API key, but the registry metadata does not declare Node or any environment variables — that's an inconsistency. Before installing or allowing the agent to invoke this skill: (1) ask the publisher to clarify and publish the required env vars (MEMOS_API_KEY, MEMOS_BASE_URL, etc.) and why they are needed; (2) verify the presence and content of ~/.claude/plugins/memos-cloud/memos-api.js and inspect it for what it sends/receives; (3) only provide an API key with minimal scope and consider using a throwaway/test key first; (4) if you cannot inspect the script, run the skill in a constrained sandbox or deny it access to secrets; (5) prefer a version that declares its requirements in the registry metadata so you can make an informed decision.
功能分析
Type: OpenClaw Skill Name: huamu668-memos-cloud Version: 1.0.0 The skill bundle provides a legitimate memory-recall and storage mechanism for the agent, interfacing with the MemOS Cloud service. It uses a local Node.js script (memos-api.js) to query an external API (memos.memtensor.cn) based on user context. The instructions in SKILL.md and README.md are transparent, follow standard plugin patterns for Claude Code/OpenClaw, and show no signs of malicious intent, data exfiltration, or harmful prompt injection.
能力评估
Purpose & Capability
The skill says it will recall memories from MemOS Cloud and instructs calling a Node script at ~/.claude/plugins/memos-cloud/memos-api.js. However the registry lists no required binaries (Node) and no required environment variables, while the README documents MEMOS_API_KEY, MEMOS_USER_ID, and MEMOS_BASE_URL. The declared requirements do not align with what the README and SKILL.md imply is needed.
Instruction Scope
SKILL.md tells the agent to run a local script (node ~/.claude/plugins/memos-cloud/memos-api.js search "{user_query}"). The package actually contains only SKILL.md and README; the referenced memos-api.js is not present in the published files. The instructions are silent about what data is sent to the remote service and do not declare the API key usage they imply. Running a local script by path can execute arbitrary code if that file exists, and the skill gives no explicit constraints on what is transmitted to MemOS endpoints.
Install Mechanism
This is instruction-only (no install spec), which minimizes installer risk. However the README documents an installation/configuration flow that writes ~/.claude/.env and expects memos-api.js to be placed under ~/.claude/plugins/memos-cloud/. That manual install behavior is not reflected in the registry metadata — a mismatch to be aware of.
Credentials
Registry metadata declares no required env vars or primary credential, but README explicitly instructs creating MEMOS_API_KEY, MEMOS_USER_ID, and MEMOS_BASE_URL in ~/.claude/.env. This is a substantive inconsistency: the skill will likely need secrets (an API key) to contact MemOS Cloud, but the published requirements do not declare them.
Persistence & Privilege
The skill is not marked always:true and is user-invocable only; it does not request persistent platform privileges in the registry metadata. There is no evidence it modifies other skills or global agent settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install huamu668-memos-cloud
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /huamu668-memos-cloud 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release: MemOS Cloud memory plugin for Claude Code
元数据
Slug huamu668-memos-cloud
版本 1.0.0
许可证
累计安装 2
当前安装数 1
历史版本数 1
常见问题

MemOS Cloud Integration 是什么?

Recall memories from MemOS Cloud before responding. Use this skill when you need context about user's previous conversations, preferences, or decisions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 411 次。

如何安装 MemOS Cloud Integration?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install huamu668-memos-cloud」即可一键安装,无需额外配置。

MemOS Cloud Integration 是免费的吗?

是的,MemOS Cloud Integration 完全免费(开源免费),可自由下载、安装和使用。

MemOS Cloud Integration 支持哪些平台?

MemOS Cloud Integration 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 MemOS Cloud Integration?

由 huamu668(@huamu668)开发并维护,当前版本 v1.0.0。

💬 留言讨论