Auto-sync: 2026-04-23 16:02
This commit is contained in:
22
wiki/entities/DeepLearningAI.md
Normal file
22
wiki/entities/DeepLearningAI.md
Normal file
@@ -0,0 +1,22 @@
|
||||
---
|
||||
title: "DeepLearning.AI"
|
||||
type: entity
|
||||
tags:
|
||||
- "AI教育"
|
||||
- "深度学习"
|
||||
- "吴恩达"
|
||||
last_updated: 2026-04-16
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
DeepLearning.AI 是由 Andrew Ng(吴恩达)创立的在线教育平台,专注于提供高质量的深度学习和机器学习课程。该平台与 [[Hugging Face]] 等开源 AI 社区紧密合作,共同推动 AI 教育的普及。
|
||||
|
||||
## Resources
|
||||
|
||||
- 官方网站:https://deeplearning.ai
|
||||
- [[learn-ai-for-free-directly-from-top-companies]] 中收录,提供免费 AI 学习课程
|
||||
|
||||
## Aliases
|
||||
- DeepLearning.AI
|
||||
- deeplearning.ai
|
||||
24
wiki/entities/IBM.md
Normal file
24
wiki/entities/IBM.md
Normal file
@@ -0,0 +1,24 @@
|
||||
---
|
||||
title: "IBM"
|
||||
type: entity
|
||||
tags:
|
||||
- "AI教育"
|
||||
- "企业AI"
|
||||
- "技能培训"
|
||||
last_updated: 2026-04-16
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
IBM(International Business Machines)是全球领先的科技企业,在 AI 领域通过 IBM SkillsBuild 平台提供免费 AI 技能培训资源。SkillsBuild 是 IBM 的人才发展计划,旨在帮助个人获得数字时代所需的技术技能。
|
||||
|
||||
## Resources
|
||||
|
||||
- 官方网站:https://skillsbuild.org
|
||||
- [[learn-ai-for-free-directly-from-top-companies]] 中收录,IBM SkillsBuild 提供免费 AI 技能培训课程
|
||||
|
||||
## Aliases
|
||||
- IBM
|
||||
- International Business Machines
|
||||
- IBM SkillsBuild
|
||||
- SkillsBuild
|
||||
34
wiki/entities/Mem0.md
Normal file
34
wiki/entities/Mem0.md
Normal file
@@ -0,0 +1,34 @@
|
||||
---
|
||||
title: "Mem0"
|
||||
type: entity
|
||||
tags: [ai-agent, memory, vector-db]
|
||||
last_updated: 2026-04-23
|
||||
---
|
||||
|
||||
## Overview
|
||||
GitHub 53.1k stars,Camp 1(Memory Backend)类别的领导者。为 AI 应用和 Agent 提供智能记忆层。
|
||||
|
||||
## Architecture
|
||||
四核心操作:add、search、update、delete
|
||||
|
||||
三层存储粒度:
|
||||
- **User level**:跨所有会话的长期用户偏好和事实
|
||||
- **Session level**:当前会话内的上下文
|
||||
- **Agent level**:Agent 自身的元记忆
|
||||
|
||||
检索机制:混合搜索(语义 + 关键词)
|
||||
|
||||
## Strengths
|
||||
- 集成最简单:Python + TypeScript SDK
|
||||
- 工作流程清晰:add → search → update → delete
|
||||
- 与任何 LLM 兼容
|
||||
|
||||
## Limitations
|
||||
- 记忆条目是**扁平**的,条目之间没有关系
|
||||
- 提取质量完全依赖 LLM extraction prompt
|
||||
- 事实存入后不进化,1月的事实和4月的事实共存
|
||||
- 无法真正"复合增长"——只是累积条目
|
||||
|
||||
## Aliases
|
||||
- Mem0
|
||||
- mem0
|
||||
@@ -1,39 +1,51 @@
|
||||
---
|
||||
title: "OpenClaw"
|
||||
type: entity
|
||||
tags: [OpenClaw, Agent, Workspace, Multi-Agent]
|
||||
sources: [multi-agent-team, 万字讲透openclaw-workspace深度解析-2026-03-21, 养龙虾5天血泪史-我的ai-agent为什么总失忆-openclaw-记忆调试全记录, daily-youtube-digest, self-healing-home-server, custom-morning-brief, second-brain, n8n-workflow-orchestration]
|
||||
last_updated: 2026-03-21
|
||||
tags: [ai-agent, memory, context-management, framework]
|
||||
last_updated: 2026-04-23
|
||||
---
|
||||
|
||||
## Overview
|
||||
开源多 Agent 框架,358k stars。以 plain markdown 文件为核心记忆架构,无隐藏状态,Agent 读什么写什么,完全透明。
|
||||
|
||||
## Architecture
|
||||
|
||||
### Core Files
|
||||
- `MEMORY.md` — 长期记忆存储
|
||||
- `YYYY-MM-DD.md` — 每日运行上下文笔记
|
||||
- `DREAMS.md` — 整合摘要(dreaming 进程的产出)
|
||||
|
||||
### Dreaming Cycle(三阶段背景整合)
|
||||
OpenClaw 的核心创新——夜间后台进程将每日笔记整合为长期记忆:
|
||||
|
||||
1. **Light Sleep**:筛选每日笔记,将相邻行分组为连贯块
|
||||
2. **REM**:基于访问频率加权提升——频繁访问的信息成为"持久真理"
|
||||
3. **Deep Sleep**:安全晋升到 MEMORY.md,执行合并而非重复
|
||||
|
||||
**评分门控**:进入长期记忆需通过六个加权信号:
|
||||
- 相关性(0.30)
|
||||
- 频率(0.24)
|
||||
- 查询多样性(0.15)
|
||||
- 时效性(0.15)
|
||||
- 整合度(0.10)
|
||||
- 概念丰富度(0.06)
|
||||
|
||||
阈值要求:分数 ≥ 0.8 + 访问次数 ≥ 3 + 独立查询数 ≥ 3
|
||||
|
||||
### 与 Camp 1 的本质区别
|
||||
Camp 1(Mem0 等):对话 → 提取事实 → 存入向量库 → 检索召回
|
||||
OpenClaw:Agent 读取结构化上下文 → 在上下文中工作 → 写回文件 → 上下文自然复合增长
|
||||
|
||||
核心哲学:**"The model only 'remembers' what gets saved to disk, there is no hidden state."**
|
||||
|
||||
## Aliases
|
||||
- OpenClaw
|
||||
- openclaw
|
||||
|
||||
## Definition
|
||||
|
||||
OpenClaw 是一个开源的 **multi-agent 框架**,核心目标是让 AI Agent 从"能用"进化到"真好用"。它通过 workspace 目录体系(AGENTS.md / SOUL.md / USER.md 等)管理 Agent 的职责定义、性格设定、用户偏好和长期记忆,实现跨会话的持续性和一致性。
|
||||
|
||||
## Core Components
|
||||
|
||||
- **workspace/**:Agent 的工作台目录(默认 `~/.openclaw/workspace/`),包含核心配置文件
|
||||
- `AGENTS.md`:工作说明书(职责、边界、多 Agent 协作)
|
||||
- `SOUL.md`:性格档案(叙事性角色设定)
|
||||
- `USER.md`:用户画像与偏好固化
|
||||
- `IDENTITY.md`:结构化身份元数据(Name/Creature/Vibe/Emoji/Avatar)
|
||||
- `TOOLS.md`:工具权限声明与使用规范
|
||||
- `MEMORY.md` / `memory/`:长期知识总表与日期滚动记忆
|
||||
- `BOOTSTRAP.md`:一次性出厂引导(完成后应删除)
|
||||
- `skills/`:技能包目录
|
||||
- **agents/<agentId>/**:各 Agent 的运行态目录(sessions、auth-profiles、models.json)
|
||||
- **openclaw.json**:总控配置,整个系统的"宪法"
|
||||
|
||||
## Key Insight
|
||||
|
||||
> OpenClaw 使用者存在一条隐形分界线:一边每次都要重新交代背景,另一边的 Agent 已知道用户是谁、该怎么说话——这条分界线就是 **workspace**。
|
||||
|
||||
## Connections
|
||||
- [[Workspace]] — OpenClaw 的核心工作目录体系
|
||||
- [[Agent-Memory]] — OpenClaw 通过 builtin/qmd 方案实现跨会话长期记忆
|
||||
- [[n8n]] — OpenClaw 通过 n8n 实现 workflow orchestration
|
||||
|
||||
- [[OpenClaw]] ← implements ← [[Context Substrate]](Camp 2 的典型代表)
|
||||
- [[Second Brain]] ← uses ← [[OpenClaw]]
|
||||
- [[Personal Knowledge Base (RAG)]] ← uses ← [[OpenClaw]]
|
||||
- [[semantic-memory-search]] ← extends ← [[OpenClaw]](MemSearch 为 Markdown 记忆添加语义搜索)
|
||||
- [[Self-Improving-Skill]] ← integrates_with ← [[OpenClaw]]
|
||||
- [[multi-channel-assistant]] ← based_on ← [[OpenClaw]]
|
||||
|
||||
Reference in New Issue
Block a user