What makes MemOS Plugin One-Click Installer notable?

2.5K downloads. Trust evidence available

How should MemOS Plugin One-Click Installer be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

MemOS Plugin One-Click Installer

Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" - "add memory plugin" - "openclaw memor... Skill: MemOS Plugin One-Click Installer Owner: mathematics-yang Summary: Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" - "add memory plugin" - "openclaw memor... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-02T03:34:43.243Z | user Add one-click MemOS install skill for OpenClaw agents - Ship SKILL.md that enables OpenClaw to autonomously i

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.5k

Updated

Oct 9, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.5K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.5K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.0release · observed Apr 2, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b1kd0rwzazfpk1jfq7gcqsx840k9s:memos-oneclick-install

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-mathematics-yang-memos-oneclick-install/snapshot"

Documentation

CLAWHUB

69,144 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: memos-local
version: 1.0.0
description: |
  Persistent local memory for OpenClaw agents.

  Use when users say:
  - "install memos"
  - "install MemOS"
  - "setup memory"
  - "add memory plugin"
  - "openclaw memory"
  - "memos onboarding"
  - "memory not working"
  - "configure memory"
  - "enable memory"
  - "upgrade MemOS"
  - "update memory plugin"

keywords:
  - memos
  - MemOS
  - memory plugin
  - persistent memory
  - local memory
  - agent memory
  - install memory
  - setup memory
  - upgrade memory
  - openclaw memory
  - task summarization
  - skill evolution
  - memory viewer
metadata:
  openclaw:
    emoji: "\U0001F9E0"
---

```
┌──────────────────────────────────────────────────────────────┐
│                                                              │
│   ███╗   ███╗███████╗███╗   ███╗ ██████╗ ███████╗            │
│   ████╗ ████║██╔════╝████╗ ████║██╔═══██╗██╔════╝            │
│   ██╔████╔██║█████╗  ██╔████╔██║██║   ██║███████╗            │
│   ██║╚██╔╝██║██╔══╝  ██║╚██╔╝██║██║   ██║╚════██║            │
│   ██║ ╚═╝ ██║███████╗██║ ╚═╝ ██║╚██████╔╝███████║            │
│   ╚═╝     ╚═╝╚══════╝╚═╝     ╚═╝ ╚═════╝ ╚══════╝            │
│                                                              │
│   persistent local memory for ai agents                      │
│                                                              │
└──────────────────────────────────────────────────────────────┘
```

# MemOS

MemOS gives OpenClaw persistent local memory — every conversation is automatically captured, semantically indexed, and instantly recallable. 100% on-device, zero cloud uploads.

Key capabilities beyond basic memory:

- **Task summarization** — Conversations are organized into structured tasks with LLM-generated summaries
- **Skill evolution** — Successful executions are distilled into reusable skills that auto-upgrade
- **Team sharing** — Hub-Client architecture for multi-agent collaborative memory
- **Memory Viewer** — Full web UI for managing memories, tasks, and skills

When talking to end users:

- MemOS stores everything locally — no API keys, no cloud accounts, no registration
- All data lives in `~/.openclaw/memos-local/memos.db` (SQLite)
- The Memory Viewer at `http://127.0.0.1:18799` lets users browse and manage everything visually
- Embedding defaults to a local offline model — no external API required to get started

---

## Trigger phrases

Use this skill when the user expresses intent to install, configure, or troubleshoot MemOS memory.

Common triggers include:

- "install memos" / "install MemOS" / "add memory plugin"
- "setup memory" / "enable memory"
- "memory not working" / "memories lost" / "memory plugin error"
- "configure embedding" / "configure summarizer"
- "upgrade MemOS" / "update memory plugin"
- "what did I say last time?" (if MemOS is not yet installed — suggest installation)

Note: Once MemOS is installed, everyday memory operations (search, recall, write) are handled by the bundled `memos-

README.md

# MemOS for OpenClaw — One-Click Install

> Chinese version: [README_zh.md](./README_zh.md).

[![npm version](https://img.shields.io/npm/v/@memtensor/memos-local-openclaw-plugin)](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/MemTensor/MemOS/blob/main/LICENSE)
[![Node.js >= 18](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org/)
[![GitHub](https://img.shields.io/badge/GitHub-Source-181717?logo=github)](https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw)

> [Homepage](https://memos-claw.openmem.net) · [Documentation](https://memos-claw.openmem.net/docs/) · [NPM](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin) · [Troubleshooting](https://memos-claw.openmem.net/docs/troubleshooting.html)

---

## What this folder contains

| File | Purpose |
| ---- | ------- |
| **`SKILL.md`** | The agent skill that drives one-click installation. Once loaded, OpenClaw reads this file and **autonomously** installs, configures, and verifies the MemOS plugin — you just answer one question. |
| **`README.md`** | This file — a human-readable overview of the installation experience and MemOS's features. |

---

## True one-click: let OpenClaw do the work

The **`SKILL.md`** in this folder is not a manual — it is a **machine-readable installation skill** designed for the OpenClaw agent. When you say *"install memos"* or *"install MemOS"*, here is what happens:

### Zero manual steps

Once triggered, OpenClaw executes a **6-step autonomous pipeline** — detecting your current state, installing the plugin, writing configuration, restarting the gateway, verifying the result, and delivering a final summary. **You do not need to run any command yourself.**

The only interaction during the entire process is a single question:

> *Choose your embedding model — local offline (A) or external API (B)?*

Reply `A` or `B`, and OpenClaw handles the rest. If you are upgrading an existing installation, even this question is skipped — the process is fully hands-free.

### Automatic OS detection — macOS, Linux, and Windows

You never need to tell the agent what system you are running. The skill uses **`process.platform`** (`darwin` / `linux` / `win32`) to detect your OS and adapts every command accordingly:

| Aspect | How it adapts |
| ------ | ------------- |
| **Path separators & home directory** | All paths are built with `require('path').join(...)` and `require('os').homedir()` — works identically on every OS. |
| **Shell commands** | The primary approach is `node -e "..."`, which runs the same way in bash, PowerShell, and cmd. Platform-specific fallbacks (e.g. `nohup` on macOS/Linux, `Start-Process` on Windows) are used only when inherently necessary. |
| **Install script fallback** | If the OpenClaw CLI is unavailable, the agent picks `install.sh` (macOS/Linux) or `install.ps1` (Windows) automatically — n

_meta.json

{
  "ownerId": "kn7122re74m5mqwg06nsnn2nwh8418kf",
  "slug": "memos-oneclick-install",
  "version": "1.0.0",
  "publishedAt": 1775100883243
}

README_zh.md

# MemOS for OpenClaw — 一键安装

> English version: [README.md](./README.md).

[![npm version](https://img.shields.io/npm/v/@memtensor/memos-local-openclaw-plugin)](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/MemTensor/MemOS/blob/main/LICENSE)
[![Node.js >= 18](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org/)
[![GitHub](https://img.shields.io/badge/GitHub-Source-181717?logo=github)](https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw)

> [主页](https://memos-claw.openmem.net) · [文档](https://memos-claw.openmem.net/docs/) · [NPM](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin) · [故障排除](https://memos-claw.openmem.net/docs/troubleshooting.html)

---

## 本目录包含

| 文件 | 用途 |
| ---- | ---- |
| **`SKILL.md`** | 驱动一键安装的 Agent 技能。加载后，OpenClaw 读取此文件并 **自主** 完成 MemOS 插件的安装、配置与验证 —— 你只需回答一个问题。 |
| **`README.md` / 本文件** | 面向人类的总览：安装体验说明与 MemOS 功能介绍。 |

---

## 真正的一键安装：让 OpenClaw 替你完成

本目录中的 **`SKILL.md`** 不是一份手册 —— 它是一份 **机器可读的安装技能**，专为 OpenClaw Agent 设计。当你对 Agent 说出 *"安装 memos"* 或 *"install MemOS"*，以下流程会自动发生：

### 零手动操作

触发后，OpenClaw 执行一条 **6 步全自主流水线** —— 检测当前状态、安装插件、写入配置、重启网关、验证结果、交付最终总结。**你不需要自己执行任何命令。**

整个过程中唯一的交互只有一个问题：

> *选择嵌入模型 —— 本地离线模型 (A) 还是外部 API (B)？*

回复 `A` 或 `B`，其余一切由 OpenClaw 处理。如果是升级现有安装，连这个问题也会跳过 —— 全程无需干预。

### 自动识别操作系统 —— macOS、Linux、Windows 全适配

你无需告诉 Agent 你在用什么系统。技能通过 **`process.platform`**（`darwin` / `linux` / `win32`）自动检测操作系统，并据此调整每一条命令：

| 方面 | 如何适配 |
| ---- | -------- |
| **路径分隔符与主目录** | 所有路径通过 `require('path').join(...)` 和 `require('os').homedir()` 构建 —— 在每个系统上表现一致。 |
| **Shell 命令** | 主要方式为 `node -e "..."`，在 bash、PowerShell 和 cmd 中行为相同。仅在固有平台差异处（如 macOS/Linux 的 `nohup`、Windows 的 `Start-Process`）使用特定回退方案。 |
| **安装脚本回退** | 若 OpenClaw CLI 不可用，Agent 会根据系统自动选择 `install.sh`（macOS/Linux）或 `install.ps1`（Windows）—— 无需用户决定。 |
| **原生模块重编译** | `better-sqlite3` 会自动重编译以匹配本地 Node.js 版本；构建工具指引也是平台感知的（`xcode-select` / `apt install build-essential` / Visual Studio Build Tools）。 |

**一句话：** 无论你是用 Mac、Linux 服务器还是 Windows 工作站，说一声 *"安装 memos"*，然后坐等即可。

### 智能状态检测

技能不会盲目重装。在动手之前它会先检查：

- **未安装** —— 执行完整安装流水线（Steps 0 – 6）。
- **已安装但版本过旧** —— 自动升级，保留你现有的配置。
- **已是最新版本** —— 仅做快速验证；除非发现问题，否则不重启。
- **配置不完整或损坏** —— 自动修复，无需重新下载插件。

每个分支都由 Agent 自主判断。你永远不会被问到 *"你想做什么？"*。

---

## MemOS 带给你什么

安装完成后，MemOS 插件将 OpenClaw 变为一个 **具有记忆能力的 Agent** —— 100% 在本地设备上运行，默认使用本地嵌入模型时无需云端账号。

### 核心能力

| 能力 | 说明 |
| ---- | ---- |
| **持久记忆** | 每一轮对话自动采集、语义分块、嵌入并索引到本地 SQLite 数据库（`~/.openclaw/memos-local/memos.db`）。无需手动说"记住这个"。 |
| **混合检索** | FTS5 关键词搜索 + 向量语义搜索，通过倒数排名融合 (RRF) 与最大边际相关性 (MMR) 重排序。可配置的时间衰减偏向近期记忆。 |
| **任务总结** | 对话自动划分为任务。已完成任务生成结构化 LLM 摘要 —— 目标、关键步骤、结果，以及保留的代码/命令/URL/报错等关键细节。 |
| **技能演化** | 高质量任务执行被提炼为可复用技能（SKILL.md 格式），相似任务出现时可 **自动升级**。内建版本历史、质量评分和自动安装功能。 |
| **团队共享** | 可选 Hub–Client 架构：Hub 存储共享数据，Client 本地保留私密数据。支持范围检索（`local` / `group` / `all`）、任务共享、技能发布/拉取、管理员审批和实时通知。 |
| **Memory View

skill-card.md

## Description:

Installs, configures, upgrades, and troubleshoots the MemOS local memory plugin for OpenClaw agents.

This skill is ready for commercial/non-commercial use.

## Publisher:

[mathematics-yang](https://clawhub.ai/user/mathematics-yang)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and OpenClaw users use this skill to add persistent local memory, semantic retrieval, task summaries, and memory-management tools to an OpenClaw agent. It guides the agent through install, configuration, upgrade, verification, and basic troubleshooting while asking the user only for embedding-model details when needed.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill gives the agent broad authority to install npm packages, modify OpenClaw configuration, restart services, and repair installations automatically.

Mitigation: Review the skill and package source before use, run it only in an environment where those changes are acceptable, and inspect configuration changes after installation.

Risk: Fallback installer paths use remote shell scripts.

Mitigation: Prefer the OpenClaw CLI or another pinned, verified package source; avoid pipe-to-shell installers unless the script source has been reviewed and trusted.

Risk: The installed plugin stores conversation memory locally and may interact with external embedding APIs if configured.

Mitigation: Use local embeddings for sensitive work, store API keys through environment-variable references when possible, and check telemetry, sharing, and memory-capture settings before enabling the plugin.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/mathematics-yang/skills/memos-oneclick-install)
- [MemOS for OpenClaw Homepage](https://memos-claw.openmem.net)
- [MemOS for OpenClaw Documentation](https://memos-claw.openmem.net/docs/)
- [MemOS for OpenClaw Troubleshooting](https://memos-claw.openmem.net/docs/troubleshooting.html)
- [NPM Package](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown guidance with shell commands and JSON configuration snippets]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Produces agent-facing installation and troubleshooting steps; the installed plugin may persist local conversation memory.]

## Skill Version(s):

1.0.0 (source: server release metadata and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 9h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.