← 返回 Skills 市场
xkzs2007

Llm Memory V8 Fix

作者 xkzs2007 · GitHub ↗ · v8.0.1 · MIT-0
cross-platform ⚠ suspicious
69
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install llm-memory-v8-fix
功能描述
LLM Memory Integration - 接口层 + 自动化钩子。安装后自动从 CNB 仓库拉取私有增强包。
使用说明 (SKILL.md)

LLM Memory Integration

⚠️ 重要安全声明

本包包含生命周期钩子，会在安装时自动执行网络操作：

钩子 触发时机 行为
postinstall.py 安装完成后 从 cnb.cool 克隆私有包
onStartup.py Gateway 启动时 检查私有包更新

请知悉：

  • ✅ 钩子会执行 git clone 命令（subprocess 调用）
  • ✅ 钩子会访问 https://cnb.cool/llm-memory-integrat/llm
  • ✅ 钩子会写入 ~/.openclaw/workspace/skills/llm-memory-integration/src/privileged/

架构说明

本包采用"公开包 + 私有包"架构：

组件 内容 风险等级
公开包（本包） 接口定义 + FTS 回退实现 🟢 低风险
私有包（CNB） 高性能实现 + 原生扩展 + API 集成 🟡 中风险

私有包来源：https://cnb.cool/llm-memory-integrat/llm

自动化安装

安装本技能后，系统会自动执行：

  1. postinstall 钩子：从 CNB 克隆私有包到 src/privileged/
  2. onStartup 钩子：检查私有包状态和更新

如需禁用自动安装：

# 安装时跳过钩子
clawhub install llm-memory-integration --no-hooks

手动安装私有包

如果自动安装失败，可手动执行：

git clone https://cnb.cool/llm-memory-integrat/llm.git \
  ~/.openclaw/workspace/skills/llm-memory-integration/src/privileged

权限声明

权限 用途
git 二进制 克隆私有包
网络访问 cnb.cool 下载私有包
写入 src/privileged/ 安装私有包
读写 ~/.openclaw/memory-tdai/ 记忆数据库

公开包功能（无私有包时）

  • ✅ FTS 全文搜索（SQLite FTS5）
  • ✅ 记忆 CRUD 操作
  • ✅ 接口定义

私有包功能（安装后）

  • 🚀 向量搜索（sqlite-vec）
  • 🚀 LLM/Embedding API 集成
  • 🚀 原生扩展加速
  • 🚀 GPU 加速

架构支持

  • ✅ x64 (x86_64)
  • ✅ ARM64 (aarch64)

版本: 8.0.1
许可: MIT-0
作者: xkzs2007

更新日志

v8.0.1

  • 🔒 修复元数据一致性：正确声明 hooks 的网络访问和 subprocess 调用
  • 📝 更新安全声明，明确告知用户钩子行为

v8.0.0

  • 🎯 新增生命周期钩子：安装后自动拉取私有包
  • 🎯 新增 onStartup 钩子：启动时自动检查更新
  • 🔄 重构为"公开包 + 私有包"架构
安全使用建议
This package is doing exactly what it says: when installed it will automatically git-clone a private 'privileged' repository from cnb.cool into ~/.openclaw/workspace/skills/llm-memory-integration/src/privileged and the gateway hook will check that repository on startup. That design is coherent but risky because code from an unfamiliar external host will be placed into your workspace and could contain native extensions or arbitrary executable code. Before installing consider: 1) Disable hooks during install (clawhub install llm-memory-integration --no-hooks) and manually inspect the remote repo (or clone to a sandbox) before copying its contents into your environment. 2) Only install if you trust the cnb.cool domain and/or maintain an internal mirror of the repo. 3) If you must auto-install, restrict network access or run the skill in an isolated environment/container. 4) Review the contents of the cloned repo (especially any native extensions, setup scripts, or code that could call external APIs) and verify signatures or hashes if available. 5) Note that many tests and functionality appear to rely on the private package; without it the public package falls back to the safe SQLite FTS implementation. If you want lower risk, keep the hooks disabled and use the public 'safe' implementation.
功能分析
Type: OpenClaw Skill Name: llm-memory-v8-fix Version: 8.0.1 The skill bundle acts as a bootstrap wrapper that downloads an external 'private package' from cnb.cool during installation via a postinstall hook (hooks/postinstall.py). While this behavior is transparently documented in SKILL.md and metadata files, the practice of fetching and executing remote code at install-time is a high-risk pattern often used to bypass static analysis. Additionally, the included test suite (tests/test_all.py) references highly intrusive system-level optimizations—such as NUMA topology tuning, IRQ isolation, and HugePage management—which are unusually low-level and potentially risky for a standard LLM memory integration skill.
能力评估
ℹ Purpose & Capability
Name/description and declared behavior align: the public package implements interfaces and a safe FTS fallback while lifecycle hooks clone a private 'privileged' package that provides high-performance/native extensions. The code and metadata consistently declare this architecture. Minor metadata mismatches exist (src/__init__ version is '7.0.0' while package metadata is '8.0.1') and many tests import 'core' modules that appear to be provided only by the private package — showing strong dependency on the cloned content.
ℹ Instruction Scope
SKILL.md explicitly documents the hooks and their actions. The hooks' code matches the documentation: postinstall.py runs git clone of the CNB repo into src/privileged/, and onStartup.py checks git status and writes logs. The instructions do not access unrelated system files or undeclared env vars. However the hooks will write files into the user's OpenClaw workspace and remove any existing privileged directory before cloning (shutil.rmtree), so they modify local filesystem in the declared skill area.
⚠ Install Mechanism
There is no packaged install spec but lifecycle hooks perform a 'git clone' from https://cnb.cool/llm-memory-integrat/llm.git — a non-well-known release host (not GitHub/GitLab/official release server). While cloning is documented, pulling arbitrary repository content from a personal/unknown domain is a higher-risk supply-chain action because that code will reside in the user's workspace and can contain native extensions or arbitrary executable code.
✓ Credentials
The skill requests only binaries (python3, sqlite3, git) and filesystem read/write access to its own OpenClaw paths and network access to the CNB endpoint. It does not request unrelated credentials or broad environment variables. The declared capabilities (subprocess calls and network access) match what the hooks perform.
✓ Persistence & Privilege
The skill is not forced-always, and does not modify other skills or system-wide configuration. Hooks run at install and gateway startup (normal lifecycle behavior). The skill does create/replace files inside its own workspace (src/privileged/) which is expected for its 'privileged package' design.
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 llm-memory-v8-fix
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /llm-memory-v8-fix 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
v8.0.1
修复元数据一致性：正确声明 hooks 的网络访问和 subprocess 调用行为
元数据
Slug llm-memory-v8-fix
版本 8.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Llm Memory V8 Fix 是什么？

LLM Memory Integration - 接口层 + 自动化钩子。安装后自动从 CNB 仓库拉取私有增强包。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 69 次。

如何安装 Llm Memory V8 Fix？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install llm-memory-v8-fix」即可一键安装，无需额外配置。

Llm Memory V8 Fix 是免费的吗？

是的，Llm Memory V8 Fix 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Llm Memory V8 Fix 支持哪些平台？

Llm Memory V8 Fix 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 Llm Memory V8 Fix？

由 xkzs2007（@xkzs2007）开发并维护，当前版本 v8.0.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论