Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context across sessions, or when managing decisions/preferences/tasks with multiple memory backends working together.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install triple-memory-skill或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install triple-memory-skill⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/triple-memory-skill/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: triple-memory version: 1.0.0 description: Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context across sessions, or when managing decisions/preferences/tasks with multiple memory backends working together. metadata: clawdbot: emoji: "🧠" requires: plugins: - memory-lancedb skills: - git-notes-memory ---
A comprehensive memory architecture combining three complementary systems for maximum context retention across sessions.
User Message
↓
[LanceDB auto-recall] → injects relevant conversation memories
↓
Agent responds (using all 3 systems)
↓
[LanceDB auto-capture] → stores preferences/decisions automatically
↓
[Git-Notes] → structured decisions with entity extraction
↓
[File updates] → persistent workspace docs
memory_recall, memory_store, memory_forgetscripts/file-search.sh{
"plugins": {
"slots": { "memory": "memory-lancedb" },
"entries": {
"memory-lancedb": {
"enabled": true,
"config": {
"embedding": { "apiKey": "${OPENAI_API_KEY}", "model": "text-embedding-3-small" },
"autoRecall": true,
"autoCapture": true
}
}
}
}
}
Add to your Clawdbot config to automatically preserve context before compaction:
{
"agents": {
"defaults": {
"compaction": {
"mode": "safeguard",
"memoryFlush": {
"enabled": true,
"softThresholdTokens": 8000,
"systemPrompt": "Session nearing compaction. Preserve context using triple memory system (git-notes, LanceDB, files).",
"prompt": "Context is at ~80%. Write session summary to memory/YYYY-MM-DD.md, update MEMORY.md if needed, store key facts to git-notes. Reply NO_REPLY when done."
}
}
}
}
}
This triggers automatic memory dump when context reaches ~80%, before any information is lost to compaction.
clawdhub install git-notes-memory
Copy scripts/file-search.sh to your workspace.
python3 skills/git-notes-memory/memory.py -p $WORKSPACE sync --start
python3 skills/git-notes-memory/memory.py -p $WORKSPACE remember \
'{"decision": "Use PostgreSQL", "reason": "Team expertise"}' \
-t architecture,database -i h
./scripts/file-search.sh "database config" 5
LanceDB handles this automatically. Manual tools:
memory_recall "query" - search conversation memorymemory_store "text" - manually store somethingmemory_forget - delete memories (GDPR)| Flag | Level | When to Use | |------|-------|-------------| | -i c | Critical | "always remember", explicit preferences | | -i h | High | Decisions, corrections, preferences | | -i n | Normal | General information | | -i l | Low | Temporary notes |
| System | Use For | |--------|---------| | LanceDB | Conversation context, auto-retrieval | | Git-Notes | Structured decisions, searchable by entity/tag | | File Search | Workspace docs, daily logs, MEMORY.md |
workspace/
├── MEMORY.md # Long-term curated memory
├── memory/
│ ├── active-context.md # Current session state
│ └── YYYY-MM-DD.md # Daily logs
├── scripts/
│ └── file-search.sh # Workspace search
└── skills/
└── git-notes-memory/ # Structured memory
Never announce memory operations to users. Just do it:
安装 Triple Memory 后,可以对 AI 说这些话来触发它
Help me get started with Triple Memory
Explains what Triple Memory does, walks through the setup, and runs a quick demo based on your current project
Use Triple Memory to complete memory system combining LanceDB auto-recall, Git-Notes str...
Invokes Triple Memory with the right parameters and returns the result directly in the conversation
What can I do with Triple Memory in my documents & notes workflow?
Lists the top use cases for Triple Memory, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/triple-memory-skill/ 目录(个人级,所有项目可用),或 .claude/skills/triple-memory-skill/(项目级)。重启 AI 客户端后,用 /triple-memory-skill 主动调用,或让 AI 根据上下文自动发现并使用。
Triple Memory 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Triple Memory 可免费安装使用。请查阅仓库了解许可证信息。
Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context across sessions, or when managing decisions/preferences/tasks with multiple memory backends working together.
Triple Memory 属于「Documents & Notes」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my documents & notes tasks using Triple Memory
Identifies repetitive steps in your workflow and sets up Triple Memory to handle them automatically