{
  "schemaVersion": "1.0",
  "item": {
    "slug": "triple-memory",
    "name": "Triple Memory",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/ktpriyatham/triple-memory",
    "canonicalUrl": "https://clawhub.ai/ktpriyatham/triple-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/triple-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=triple-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/SETUP.md",
      "scripts/file-search.sh"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "triple-memory",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T13:09:50.103Z",
      "expiresAt": "2026-05-08T13:09:50.103Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=triple-memory",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=triple-memory",
        "contentDisposition": "attachment; filename=\"triple-memory-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "triple-memory"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/triple-memory"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/triple-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/triple-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/triple-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/triple-memory/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Triple Memory System",
        "body": "A comprehensive memory architecture combining three complementary systems for maximum context retention across sessions."
      },
      {
        "title": "Architecture Overview",
        "body": "User Message\n     ↓\n[LanceDB auto-recall] → injects relevant conversation memories\n     ↓\nAgent responds (using all 3 systems)\n     ↓\n[LanceDB auto-capture] → stores preferences/decisions automatically\n     ↓\n[Git-Notes] → structured decisions with entity extraction\n     ↓\n[File updates] → persistent workspace docs"
      },
      {
        "title": "1. LanceDB (Conversation Memory)",
        "body": "Auto-recall: Relevant memories injected before each response\nAuto-capture: Preferences/decisions/facts stored automatically\nTools: memory_recall, memory_store, memory_forget\nTriggers: \"remember\", \"prefer\", \"my X is\", \"I like/hate/want\""
      },
      {
        "title": "2. Git-Notes Memory (Structured, Local)",
        "body": "Branch-aware: Memories isolated per git branch\nEntity extraction: Auto-extracts topics, names, concepts\nImportance levels: critical, high, normal, low\nNo external API calls"
      },
      {
        "title": "3. File Search (Workspace)",
        "body": "Searches: MEMORY.md, memory/*.md, any workspace file\nScript: scripts/file-search.sh"
      },
      {
        "title": "Enable LanceDB Plugin",
        "body": "{\n  \"plugins\": {\n    \"slots\": { \"memory\": \"memory-lancedb\" },\n    \"entries\": {\n      \"memory-lancedb\": {\n        \"enabled\": true,\n        \"config\": {\n          \"embedding\": { \"apiKey\": \"${OPENAI_API_KEY}\", \"model\": \"text-embedding-3-small\" },\n          \"autoRecall\": true,\n          \"autoCapture\": true\n        }\n      }\n    }\n  }\n}"
      },
      {
        "title": "Install Git-Notes Memory",
        "body": "clawdhub install git-notes-memory"
      },
      {
        "title": "Create File Search Script",
        "body": "Copy scripts/file-search.sh to your workspace."
      },
      {
        "title": "Session Start (Always)",
        "body": "python3 skills/git-notes-memory/memory.py -p $WORKSPACE sync --start"
      },
      {
        "title": "Store Important Decisions",
        "body": "python3 skills/git-notes-memory/memory.py -p $WORKSPACE remember \\\n  '{\"decision\": \"Use PostgreSQL\", \"reason\": \"Team expertise\"}' \\\n  -t architecture,database -i h"
      },
      {
        "title": "Search Workspace Files",
        "body": "./scripts/file-search.sh \"database config\" 5"
      },
      {
        "title": "Conversation Memory (Automatic)",
        "body": "LanceDB handles this automatically. Manual tools:\n\nmemory_recall \"query\" - search conversation memory\nmemory_store \"text\" - manually store something\nmemory_forget - delete memories (GDPR)"
      },
      {
        "title": "Importance Levels",
        "body": "FlagLevelWhen to Use-i cCritical\"always remember\", explicit preferences-i hHighDecisions, corrections, preferences-i nNormalGeneral information-i lLowTemporary notes"
      },
      {
        "title": "When to Use Each System",
        "body": "SystemUse ForLanceDBConversation context, auto-retrievalGit-NotesStructured decisions, searchable by entity/tagFile SearchWorkspace docs, daily logs, MEMORY.md"
      },
      {
        "title": "File Structure",
        "body": "workspace/\n├── MEMORY.md              # Long-term curated memory\n├── memory/\n│   ├── active-context.md  # Current session state\n│   └── YYYY-MM-DD.md      # Daily logs\n├── scripts/\n│   └── file-search.sh     # Workspace search\n└── skills/\n    └── git-notes-memory/  # Structured memory"
      },
      {
        "title": "Silent Operation",
        "body": "Never announce memory operations to users. Just do it:\n\n❌ \"I'll remember this\"\n❌ \"Saving to memory\"\n✅ (silently store and continue)"
      }
    ],
    "body": "Triple Memory System\n\nA comprehensive memory architecture combining three complementary systems for maximum context retention across sessions.\n\nArchitecture Overview\nUser Message\n     ↓\n[LanceDB auto-recall] → injects relevant conversation memories\n     ↓\nAgent responds (using all 3 systems)\n     ↓\n[LanceDB auto-capture] → stores preferences/decisions automatically\n     ↓\n[Git-Notes] → structured decisions with entity extraction\n     ↓\n[File updates] → persistent workspace docs\n\nThe Three Systems\n1. LanceDB (Conversation Memory)\nAuto-recall: Relevant memories injected before each response\nAuto-capture: Preferences/decisions/facts stored automatically\nTools: memory_recall, memory_store, memory_forget\nTriggers: \"remember\", \"prefer\", \"my X is\", \"I like/hate/want\"\n2. Git-Notes Memory (Structured, Local)\nBranch-aware: Memories isolated per git branch\nEntity extraction: Auto-extracts topics, names, concepts\nImportance levels: critical, high, normal, low\nNo external API calls\n3. File Search (Workspace)\nSearches: MEMORY.md, memory/*.md, any workspace file\nScript: scripts/file-search.sh\nSetup\nEnable LanceDB Plugin\n{\n  \"plugins\": {\n    \"slots\": { \"memory\": \"memory-lancedb\" },\n    \"entries\": {\n      \"memory-lancedb\": {\n        \"enabled\": true,\n        \"config\": {\n          \"embedding\": { \"apiKey\": \"${OPENAI_API_KEY}\", \"model\": \"text-embedding-3-small\" },\n          \"autoRecall\": true,\n          \"autoCapture\": true\n        }\n      }\n    }\n  }\n}\n\nInstall Git-Notes Memory\nclawdhub install git-notes-memory\n\nCreate File Search Script\n\nCopy scripts/file-search.sh to your workspace.\n\nUsage\nSession Start (Always)\npython3 skills/git-notes-memory/memory.py -p $WORKSPACE sync --start\n\nStore Important Decisions\npython3 skills/git-notes-memory/memory.py -p $WORKSPACE remember \\\n  '{\"decision\": \"Use PostgreSQL\", \"reason\": \"Team expertise\"}' \\\n  -t architecture,database -i h\n\nSearch Workspace Files\n./scripts/file-search.sh \"database config\" 5\n\nConversation Memory (Automatic)\n\nLanceDB handles this automatically. Manual tools:\n\nmemory_recall \"query\" - search conversation memory\nmemory_store \"text\" - manually store something\nmemory_forget - delete memories (GDPR)\nImportance Levels\nFlag\tLevel\tWhen to Use\n-i c\tCritical\t\"always remember\", explicit preferences\n-i h\tHigh\tDecisions, corrections, preferences\n-i n\tNormal\tGeneral information\n-i l\tLow\tTemporary notes\nWhen to Use Each System\nSystem\tUse For\nLanceDB\tConversation context, auto-retrieval\nGit-Notes\tStructured decisions, searchable by entity/tag\nFile Search\tWorkspace docs, daily logs, MEMORY.md\nFile Structure\nworkspace/\n├── MEMORY.md              # Long-term curated memory\n├── memory/\n│   ├── active-context.md  # Current session state\n│   └── YYYY-MM-DD.md      # Daily logs\n├── scripts/\n│   └── file-search.sh     # Workspace search\n└── skills/\n    └── git-notes-memory/  # Structured memory\n\nSilent Operation\n\nNever announce memory operations to users. Just do it:\n\n❌ \"I'll remember this\"\n❌ \"Saving to memory\"\n✅ (silently store and continue)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ktpriyatham/triple-memory",
    "publisherUrl": "https://clawhub.ai/ktpriyatham/triple-memory",
    "owner": "ktpriyatham",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/triple-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/triple-memory",
    "agentUrl": "https://openagent3.xyz/skills/triple-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/triple-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/triple-memory/agent.md"
  }
}