Skill：llm wiki cli
Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.
适用场景
招聘人事
适合角色
介绍
以下内容整理自开源仓库 `JanYork/llm-wiki-cli` 的 README / SKILL.md 摘要： <h1 align="center">LWC — Proactive Memory for AI Agents</h1> <p align="center"> <strong>Agent-driven · Persistent · Source-grounded</strong> </p> <p align="center"> <a href="https://www.npmjs.com/package/@i-xor/lwc"><img alt="npm: @i-xor/lwc" src="https://img.shields.io/badge/npm-%40i--xor%2Flwc-CB3837?logo=npm"></a> <a href="https://crates.io/crates/lwc"><img alt="crates.io: lwc" src="https://img.shields.io/crates/v/lwc.svg"></a> <img alt="Node.js 22 or newer" src="https://img.shields.io/badge/node-%3E%3D22-5FA04E?logo=nodedotjs"> <img alt="Platform: macOS, Linux, Windows" src="https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-666666"> <a href="https://github.com/JanYork/llm-wiki-cli/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/JanYork/llm-wiki-cli/actions/workflows/ci.yml/badge.svg"></a> <a href="https://skills.sh/janyork/llm-wiki-cli/using-lwc"><img alt="skills.sh: using-lwc" src="https://img.shields.io/badge/skills.sh-using--lwc-000000?logo=vercel"></a> <a href="LICENSE"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/license-Apache--2.0-blue.svg"></a> </p> <p align="center"> <a href="README.md">English</a> · <a href="README.zh-CN.md">简体中文</a> · <a href="docs/readme/README.ja.md">日本語</a> · <a href="docs/readme/README.es.md">Español</a> · <a href="docs/readme/README.pt-BR.md">Português (Brasil)</a> · <a href="docs/readme/README.fr.md">Français</a> · <a href="docs/readme/README.ru.md">Русский</a> </p> <p align="center"> <img src="https://raw.githubusercontent.com/JanYork/llm-wiki-cli/main/docs/images/lwc-social-preview.png" alt="LWC — Proactive Memory for AI Agents" width="100%"> </p> `lwc` is an agent-driven proactive memory CLI for AI agents. It lets Agents autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions. **Works with Claude Code, Codex, Cursor, OpenCode, Gemini CLI, Kiro, Hermes, Antigravity, GitHub Copilot in VS Code, Copilot CLI, Copilot for JetBrains, and pi.** LWC turns curated documents into a durable Wiki. Agents reason and synthesize; `lwc` preserves sources, pages, citations, links, indexes, and history so knowledge compounds instead of being rediscovered from raw chunks on every query. <p align="center"> <img src="https://raw.githubusercontent.com/JanYork/llm-wiki-cli/main/docs/images/lwc-overview-en.png" alt="LWC product overview" width="820"> </p> ## Self-hosted team memory — v0.19.3 LWC team spaces keep core memory in local SQLite and Wiki files and synchronize it automatically through a self-hosted server. External Agents resolve conflicts through CLI/MCP; LWC does not embed an LLM. The team console supports English and Simplified Chinese, explicit space permissions, device/Agent access an --- **说明**：内容由公开仓库整理，使用前请自行核对是否适合你的场景。
安装方式
1. 打开仓库：https://github.com/JanYork/llm-wiki-cli 2. 查找 SKILL.md 或 README 中的安装章节 3. 克隆或下载所需 Skill 子目录到本地 skills 路径（如 `.cursor/skills/` 或 `.claude/skills/`） 4. 重启 / 重载 Agent 客户端 5. 用一条真实任务验证 Skill 是否被正确加载
适用平台
- Cursor
- Claude
- Codex