Auto-sync: 2026-04-17 13:17
This commit is contained in:
29
wiki/concepts/Cron-Jobs.md
Normal file
29
wiki/concepts/Cron-Jobs.md
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
title: "Cron Jobs"
|
||||
type: concept
|
||||
tags: [automation, scheduling, linux]
|
||||
sources: [self-healing-home-server-infrastructure-management]
|
||||
last_updated: 2026-04-17
|
||||
---
|
||||
|
||||
## Summary
|
||||
Cron Jobs(定时任务)是 Linux 系统中基于时间的任务调度机制,允许用户在特定时间间隔或时间点自动执行命令或脚本。在 AI Agent 场景中,定时作业是提供持续价值的关键机制。
|
||||
|
||||
## Definition
|
||||
基于 crontab 的时间调度系统,通过配置文件定义任务执行的时间规则。
|
||||
|
||||
## Key Characteristics
|
||||
- 基于时间调度(每分钟、每小时、每天等)
|
||||
- 后台运行,无需人工干预
|
||||
- 可用于自动化监控、备份、清理等任务
|
||||
|
||||
## Use Cases in AI Agent
|
||||
- 健康检查:定时检测服务状态
|
||||
- 数据处理:定时处理新数据
|
||||
- 日志分析:定时分析日志发现异常
|
||||
- 邮件分类:定时扫描邮箱
|
||||
- 每日简报:定时生成并发送报告
|
||||
|
||||
## Connections
|
||||
- [[Self-Healing Systems]] ← uses ← [[Cron Jobs]]:自愈系统使用 cron 作业进行定时检查
|
||||
- [[Agentic AI]] ← executes ← [[Cron Jobs]]:AI Agent 执行定时任务实现自动化
|
||||
30
wiki/concepts/Defense-in-Depth.md
Normal file
30
wiki/concepts/Defense-in-Depth.md
Normal file
@@ -0,0 +1,30 @@
|
||||
---
|
||||
title: "Defense in Depth"
|
||||
type: concept
|
||||
tags: [security, architecture, risk-mitigation]
|
||||
sources: [self-healing-home-server-infrastructure-management]
|
||||
last_updated: 2026-04-17
|
||||
---
|
||||
|
||||
## Summary
|
||||
Defense in Depth(纵深防御)是一种多层安全架构策略,通过在多个层面部署安全控制来保护系统,即使某一层被突破,其他层仍能提供保护。在 AI Agent 安全设置中尤为重要。
|
||||
|
||||
## Definition
|
||||
通过在网络、主机、应用和数据多个层面部署互补的安全控制,实现全面防护的安全架构。
|
||||
|
||||
## Key Layers
|
||||
1. **网络层**:网络分段、防火墙、入侵检测
|
||||
2. **主机层**:访问控制、系统加固、监控
|
||||
3. **应用层**:输入验证、安全扫描、审计日志
|
||||
4. **数据层**:加密、访问控制、备份
|
||||
|
||||
## AI Agent Security Application
|
||||
- 专用 1Password vault 限制 AI 访问范围
|
||||
- 网络分段隔离敏感服务
|
||||
- 每日安全审计检查特权容器、硬编码 secrets、过度宽松权限
|
||||
- 分支保护:PR 必须人工审查,Agent 无法覆盖
|
||||
|
||||
## Connections
|
||||
- [[TruffleHog]] ← implements ← [[Defense in Depth]]:TruffleHog 扫描实现应用层安全
|
||||
- [[Gitea]] ← enables ← [[Defense in Depth]]:本地 Git 作为防御层
|
||||
- [[Zero Trust Architecture]] ← related_to ← [[Defense in Depth]]:纵深防御是零信任的基础
|
||||
30
wiki/concepts/Knowledge-Extraction.md
Normal file
30
wiki/concepts/Knowledge-Extraction.md
Normal file
@@ -0,0 +1,30 @@
|
||||
---
|
||||
title: "Knowledge Extraction"
|
||||
type: concept
|
||||
tags: [ai, knowledge-management, automation]
|
||||
sources: [self-healing-home-server-infrastructure-management]
|
||||
last_updated: 2026-04-17
|
||||
---
|
||||
|
||||
## Summary
|
||||
Knowledge Extraction(知识提取)是指 AI Agent 从非结构化或半结构化数据源(如笔记、对话记录、邮件)中提取有价值信息并转化为结构化、可查询知识库的过程。
|
||||
|
||||
## Definition
|
||||
将分散的、非结构化的信息通过 AI 处理转化为结构化、可复用知识的技术。
|
||||
|
||||
## Key Characteristics
|
||||
- 从多种来源提取信息(Obsidian 笔记、ChatGPT 对话导出、邮件)
|
||||
- 转化为原子事实(atomic facts)
|
||||
- 构建可搜索的知识库
|
||||
- 随着时间推移价值递增
|
||||
|
||||
## Benefits
|
||||
- 将个人知识资产结构化
|
||||
- 创建可搜索的知识库
|
||||
- 随时间累积价值(一个用户从 ChatGPT 历史中提取了 49,079 个原子事实)
|
||||
- 支持 AI Agent 的上下文记忆
|
||||
|
||||
## Connections
|
||||
- [[Obsidian]] ← stores ← [[Knowledge Extraction]]:Obsidian 笔记是知识提取的来源之一
|
||||
- [[Agentic AI]] ← performs ← [[Knowledge Extraction]]:AI Agent 执行知识提取
|
||||
- [[Knowledge Network]] ← built_by ← [[Knowledge Extraction]]:知识提取构建知识网络
|
||||
31
wiki/concepts/Morning-Briefing.md
Normal file
31
wiki/concepts/Morning-Briefing.md
Normal file
@@ -0,0 +1,31 @@
|
||||
---
|
||||
title: "Morning Briefing"
|
||||
type: concept
|
||||
tags: [automation, reporting, ai-agent]
|
||||
sources: [self-healing-home-server-infrastructure-management]
|
||||
last_updated: 2026-04-17
|
||||
---
|
||||
|
||||
## Summary
|
||||
Morning Briefing(每日简报)是 AI Agent 定时生成的综合报告,包含天气、日历、系统健康、任务状态等信息,在每天早晨自动交付给用户。
|
||||
|
||||
## Definition
|
||||
AI Agent 每天定时生成并发送的综合报告,汇总多个数据源的关键信息。
|
||||
|
||||
## Typical Content
|
||||
- **天气**:当前条件和预报
|
||||
- **日历**:当天事件、冲突检测
|
||||
- **系统健康**:CPU/RAM/存储、服务状态、最近部署、告警
|
||||
- **任务看板**:昨日完成、进行中、阻塞项
|
||||
- **亮点**:夜间脑暴要点、待处理邮件、本周截止
|
||||
|
||||
## Value
|
||||
- 用户早晨快速了解全局状态
|
||||
- 无需手动检查多个系统
|
||||
- 自动化日常信息汇总
|
||||
- 支持远程运维(如边遛狗边处理部署问题)
|
||||
|
||||
## Connections
|
||||
- [[Agentic AI]] ← generates ← [[Morning Briefing]]:AI Agent 生成每日简报
|
||||
- [[Cron Jobs]] ← triggers ← [[Morning Briefing]]:定时任务触发简报生成
|
||||
- [[K3s]] ← monitored_by ← [[Morning Briefing]]:K3s 集群健康状态包含在简报中
|
||||
27
wiki/concepts/YouTube-Digest.md
Normal file
27
wiki/concepts/YouTube-Digest.md
Normal file
@@ -0,0 +1,27 @@
|
||||
---
|
||||
title: "YouTube Digest"
|
||||
type: concept
|
||||
tags: [agent-workflow, automation]
|
||||
date: 2026-04-17
|
||||
---
|
||||
|
||||
## Source
|
||||
- [[raw/Agent/usecases/daily-youtube-digest.md]]
|
||||
|
||||
## Definition
|
||||
AI Agent 自动从订阅的 YouTube 频道获取最新视频并生成每日摘要的工作流。
|
||||
|
||||
## When to Use
|
||||
- 每天早晨获取感兴趣频道的更新
|
||||
- 追踪特定关键词相关的新视频
|
||||
- 替代不可靠的 YouTube 官方通知
|
||||
|
||||
## How It Works
|
||||
1. 使用 youtube-full skill 的 `channel/latest` 获取频道最新视频
|
||||
2. 获取视频 Transcript(消耗积分)
|
||||
3. 用 AI 总结要点
|
||||
4. 推送 digest(每日定时或按需)
|
||||
|
||||
## Related Concepts
|
||||
- [[Agent-Chain]]:多个 Agent 串联工作
|
||||
- [[TranscriptAPI]]:视频转录服务
|
||||
26
wiki/concepts/youtube-full-skill.md
Normal file
26
wiki/concepts/youtube-full-skill.md
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
title: "youtube-full skill"
|
||||
type: concept
|
||||
tags: [skill, openclaw, youtube]
|
||||
date: 2026-04-17
|
||||
---
|
||||
|
||||
## Source
|
||||
- [[raw/Agent/usecases/daily-youtube-digest.md]]
|
||||
|
||||
## Definition
|
||||
OpenClaw 的 YouTube 集成 skill,提供频道视频获取和 Transcript 获取能力。
|
||||
|
||||
## Key Features
|
||||
- `channel/latest`:获取频道最新视频(免费)
|
||||
- `channel/resolve`:解析频道 handle(免费)
|
||||
- 获取视频 Transcript(消耗积分)
|
||||
- 集成 TranscriptAPI.com API
|
||||
|
||||
## Credits
|
||||
- 注册赠送 100 免费积分
|
||||
- channel 操作免费,仅 Transcript 消耗积分
|
||||
|
||||
## Related Entities
|
||||
- [[OpenClaw]]:运行 skill 的 AI Agent 平台
|
||||
- [[TranscriptAPI]]:提供视频转录的 API 服务
|
||||
Reference in New Issue
Block a user