What makes Llm Memory V9 notable?

1.9K downloads. Trust evidence available

How should Llm Memory V9 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

Llm Memory V9

LLM Memory Integration - 公开框架包。通过环境变量链接本地私有配置，实现公私分离。 Skill: Llm Memory V9 Owner: xkzs2007 Summary: LLM Memory Integration - 公开框架包。通过环境变量链接本地私有配置，实现公私分离。 Tags: ann:3.2.3, avx512:3.2.3, cuda:3.2.0, embedding:3.2.3, gpu:3.2.3, hnsw:3.2.3, hybrid:1.0.9, ima:3.2.0, latest:9.0.1, llm:3.2.3, memory:3.2.3, quantization:3.2.3, rrf:1.0.9, search:3.2.3, simd:3.2.0, vector:3.2.3, vmp:3.2.0 Version history: v9.0.1 | 2026-04-16T03:45:27.241Z | user 修复权限声明：移除未使用的路径声明，仅访问用户指定的 CNB_PRI

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.9k

Updated

Oct 9, 2026

Version

9.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K 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: 1.9K downloadsadoption · observed Oct 9, 2026
Latest release: 9.0.1release · observed Apr 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1790dhc286tsqnpg6s6c1r9ex8486x6:llm-memory-integration

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
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-xkzs2007-llm-memory-integration/snapshot"

Documentation

CLAWHUB

127,942 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: llm-memory-integration
description: LLM Memory Integration - 公开框架包。通过环境变量链接本地私有配置，实现公私分离。
version: 9.0.1
license: MIT-0
author: xkzs2007
homepage: https://clawhub.ai/skill/llm-memory-integration

metadata:
  openclaw:
    emoji: "🧠"
    requires:
      bins:
        - python3
      envVars:
        optional:
          - CNB_PRIVATE_WORKSPACE
    hooks:
      postinstall: hooks/bootstrap-extra-files.py
---

# LLM Memory Integration

## 概述

本技能是一个**公开框架包**，通过环境变量链接本地私有配置。

**核心设计**：公开框架 + 本地私有配置

| 组件 | 位置 | 内容 |
|------|------|------|
| **公开包** | ClawHub | 框架 + 模板 + 钩子 |
| **私有配置** | 用户本地（CNB_PRIVATE_WORKSPACE） | 自定义规则和实现 |

## 安全特性

- ✅ **无网络访问**：不执行任何网络操作
- ✅ **无远程拉取**：不从远程仓库下载代码
- ✅ **无敏感信息**：不包含任何密钥或私有地址
- ✅ **用户可控**：私有配置完全由用户控制
- ✅ **最小权限**：仅访问用户指定的 `CNB_PRIVATE_WORKSPACE` 目录

## 权限说明

| 权限 | 用途 |
|------|------|
| `python3` | 运行钩子脚本 |
| `CNB_PRIVATE_WORKSPACE`（可选） | 用户指定的私有配置目录 |

**注意**：本技能不访问 `~/.openclaw/memory-tdai` 或任何其他系统路径。

## 使用方法

### 基础使用（无私有配置）

```bash
clawhub install llm-memory-integration
```

### 高级使用（带私有配置）

1. **创建私有配置目录**

```bash
mkdir -p ~/my-private-config
```

2. **设置环境变量**

```bash
# 添加到 ~/.bashrc 或 ~/.zshrc
export CNB_PRIVATE_WORKSPACE="$HOME/my-private-config"
```

3. **放置私有文件**

```
~/my-private-config/
├── AGENTS.md          # 自定义 Agent 规则
├── TOOLS.md           # 自定义工具配置
├── MEMORY.md          # 私有记忆文件
└── config/            # 自定义配置
```

4. **安装技能**

```bash
clawhub install llm-memory-integration
```

## 钩子说明

| 钩子 | 功能 |
|------|------|
| `bootstrap-extra-files.py` | 将 `CNB_PRIVATE_WORKSPACE` 目录链接到工作区 |

钩子只执行本地文件操作（symlink/copy），仅访问用户指定的目录。

## 架构支持

- ✅ x64 (x86_64)
- ✅ ARM64 (aarch64)

---

**版本**: 9.0.1  
**许可**: MIT-0  
**作者**: xkzs2007

## 更新日志

### v9.0.1
- 🔒 **修复权限声明**：移除未使用的 `~/.openclaw/memory-tdai` 路径声明
- 📝 **完善文档**：明确说明仅访问 `CNB_PRIVATE_WORKSPACE`

### v9.0.0
- 🔄 **架构重构**：从"远程拉取"改为"本地链接"
- 🔒 **安全增强**：无网络访问、无敏感信息暴露
- 📁 **公私分离**：公开框架 + 本地私有配置

hooks/README.md

# Hooks 说明

本目录包含生命周期钩子，用于在安装时自动配置私有内容。

## 钩子列表

| 钩子 | 触发时机 | 功能 |
|------|---------|------|
| `bootstrap-extra-files.py` | postinstall | 将本地私有配置链接到工作区 |

## 安全说明

- ✅ **无网络访问**：钩子不执行任何网络操作
- ✅ **无敏感信息**：钩子只读取环境变量，不包含任何密钥或地址
- ✅ **无远程拉取**：钩子只操作本地文件系统
- ✅ **用户可控**：用户完全控制私有目录的位置和内容

## 使用方法

### 1. 准备私有配置目录

```bash
mkdir -p ~/my-private-config
# 将你的私有文件放入此目录
```

### 2. 设置环境变量

```bash
# 临时设置（当前会话）
export CNB_PRIVATE_WORKSPACE="~/my-private-config"

# 永久设置（添加到 ~/.bashrc 或 ~/.zshrc）
echo 'export CNB_PRIVATE_WORKSPACE="$HOME/my-private-config"' >> ~/.bashrc
```

### 3. 安装技能

```bash
clawhub install llm-memory-integration
```

安装后，钩子会自动将 `CNB_PRIVATE_WORKSPACE` 目录下的文件链接到技能工作区。

## 私有目录结构示例

```
~/my-private-config/
├── AGENTS.md          # 自定义 Agent 规则
├── TOOLS.md           # 自定义工具配置
├── MEMORY.md          # 私有记忆文件
└── config/            # 自定义配置目录
    └── llm_config.json
```

## 禁用钩子

如果不需要私有配置，可以跳过钩子：

```bash
clawhub install llm-memory-integration --no-hooks
```

workspace_template/README.md

# Workspace 模板

此目录包含公开的模板文件，作为默认配置。

## 文件说明

| 文件 | 说明 |
|------|------|
| `AGENTS.md` | Agent 规则模板 |
| `TOOLS.md` | 工具配置模板 |

## 使用方法

这些模板文件会在安装时复制到技能目录。如果用户设置了 `CNB_PRIVATE_WORKSPACE` 环境变量，私有文件会覆盖这些模板。

_meta.json

{
  "ownerId": "kn78fxerps76taazjrm4v4ytn1849v0j",
  "slug": "llm-memory-integration",
  "version": "9.0.1",
  "publishedAt": 1776311127241
}

skill-card.md

## Description:

Llm Memory V9 provides a public framework for linking a user-specified local private configuration directory into an agent skill workspace.

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

## Publisher:

[xkzs2007](https://clawhub.ai/user/xkzs2007)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent operators use this skill to keep public workspace templates separate from private local memory, agent rules, tool configuration, and other user-controlled files.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The postinstall hook can link or copy broad private local content into the trusted skill directory.

Mitigation: Set CNB_PRIVATE_WORKSPACE only to a narrow, reviewed directory containing files intended for agent use.

Risk: Imported private files such as AGENTS.md, TOOLS.md, MEMORY.md, scripts, or config files can affect agent behavior after installation.

Mitigation: Review private workspace contents before installation and avoid home folders, synced folders, or shared directories.

Risk: Users who do not need private configuration import still receive an install hook path.

Mitigation: Install with hooks disabled when private local configuration import is not required.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/xkzs2007/skills/llm-memory-integration)
- [Hook documentation](artifact/hooks/README.md)
- [Workspace template documentation](artifact/workspace_template/README.md)

## Skill Output:

**Output Type(s):** [Files, Configuration, Guidance, Shell commands]

**Output Format:** [Markdown guidance and local workspace files or symlinks]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses optional CNB_PRIVATE_WORKSPACE to link or copy user-controlled local files at install time.]

## Skill Version(s):

9.0.1 (source: frontmatter, package.json, release metadata)

## 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 7h 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.