{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-enhanced-memory",
    "name": "Enhanced Memory",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/fatcatMaoFei/openclaw-enhanced-memory",
    "canonicalUrl": "https://clawhub.ai/fatcatMaoFei/openclaw-enhanced-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-enhanced-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-enhanced-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/architecture.md",
      "scripts/memory_lifecycle_manager.py",
      "scripts/memory_retrieval_strategy.py",
      "scripts/memory_tag_search.py"
    ],
    "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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/openclaw-enhanced-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/openclaw-enhanced-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-enhanced-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-enhanced-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-enhanced-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": "Enhanced Memory",
        "body": "A structured memory system that gives your OpenClaw agent organized, searchable, long-lived memory instead of a single monolithic MEMORY.md."
      },
      {
        "title": "Why?",
        "body": "The default MEMORY.md approach hits a wall fast:\n\nOne file grows endlessly → slow to read, expensive on tokens\nNo categorization → food logs mixed with project notes mixed with relationship context\nNo retrieval strategy → agent re-reads everything or misses what matters\nNo lifecycle → old entries clutter active memory forever\n\nTagged Memory fixes all of this."
      },
      {
        "title": "1. Hierarchical Directory Organization",
        "body": "Memories are stored in purpose-built directories:\n\nmemory/\n├── current/          # Active memories (last 6 months)\n├── archived/         # Auto-archived older memories (permanent, never deleted)\n│   └── YYYY-MM/      # Organized by month\n├── RELATION/         # One file per person (relationship context)\n├── food/             # Meal and food logs\n├── training/         # Exercise and workout records\n├── connections.md    # Global relationship graph\n├── system/           # System config and logs\n└── misc/             # Everything else"
      },
      {
        "title": "2. Tag-Based Indexing",
        "body": "Tag any line in any memory file with [category:value] markers:\n\n## 2026-02-20\n\n- Had lunch with Zhang Hao [人物:张浩东] [类型:聚餐] [地点:campus]\n- Discussed the new project deadline [项目:openclaw] [类型:会议]\n- Yoyo learned a new trick today [宠物:悠悠] [类型:milestone]\n\nTags support multi-tag AND search — find the exact memory you need:\n\n# Single tag search\npython3 scripts/memory_tag_search.py \"人物:张浩东\"\n\n# Multi-tag AND search (all tags must match)\npython3 scripts/memory_tag_search.py \"人物:王隆哲\" \"类型:开票信息\"\n\n# List all tags in the system\npython3 scripts/memory_tag_search.py --list-tags\n\n# List tags under a specific category\npython3 scripts/memory_tag_search.py --list-tags --category 人物"
      },
      {
        "title": "3. Lifecycle Management",
        "body": "Memories age gracefully — never lost, always accessible:\n\nAgeLocationStatus0–6 monthsmemory/current/Active, auto-retrieved6–12 monthsmemory/archived/YYYY-MM/Archived, searchable on demand12+ monthsmemory/archived/Permanent archive, manual query\n\nRun the lifecycle manager manually or via cron:\n\n# Default: archive memories older than 6 months\npython3 scripts/memory_lifecycle_manager.py\n\n# Custom threshold (e.g., 90 days)\npython3 scripts/memory_lifecycle_manager.py 90"
      },
      {
        "title": "4. Smart Cross-Category Retrieval",
        "body": "The retrieval strategy script auto-classifies queries and searches the right directories:\n\npython3 scripts/memory_retrieval_strategy.py \"What did I eat yesterday?\"\n# → Searches memory/food/ + memory/current/\n\npython3 scripts/memory_retrieval_strategy.py \"How is Yoyo doing?\"\n# → Searches memory/RELATION/悠悠.md + memory/connections.md\n\npython3 scripts/memory_retrieval_strategy.py \"Yang Lingxiao\"\n# → Searches memory/RELATION/ + memory/connections.md\n\nQuery type detection covers: food, training, relationships, pets, system, mood, projects, and more."
      },
      {
        "title": "Scripts",
        "body": "ScriptPurposescripts/memory_tag_search.pyTag-based indexing and search (single/multi-tag AND queries, tag listing)scripts/memory_retrieval_strategy.pySmart retrieval — auto-classifies queries and routes to relevant memory directoriesscripts/memory_lifecycle_manager.pyAutomatic archival of old memories (configurable threshold, never deletes)"
      },
      {
        "title": "AGENTS.md",
        "body": "Add the following to your AGENTS.md memory section:\n\n## Memory\n\n### Directory Structure\n- `memory/current/` — active memories (6 months)\n- `memory/archived/` — permanent archive\n- `memory/RELATION/` — per-person relationship files\n- `memory/food/` — meal logs\n- `memory/training/` — workout logs\n\n### Retrieval Strategy\n- Exact queries (names, dates, codes) → `grep` the file system\n- Fuzzy/semantic queries → `python3 scripts/memory_retrieval_strategy.py \"<query>\"`\n- Tag search → `python3 scripts/memory_tag_search.py \"<category>:<value>\"`\n\n### Tagging Convention\nWhen writing memory entries, tag important lines:\n  [人物:name] [类型:type] [地点:place] [项目:project] [情绪:mood]"
      },
      {
        "title": "HEARTBEAT.md",
        "body": "Add periodic memory maintenance to your heartbeat checklist:\n\n## Memory Maintenance (every few days)\n- [ ] Run `python3 scripts/memory_lifecycle_manager.py` to archive old memories\n- [ ] Run `python3 scripts/memory_tag_search.py --list-tags` to review tag health\n- [ ] Check `memory/current/` file count — if growing large, verify archival is running"
      },
      {
        "title": "Cron (optional)",
        "body": "Set up monthly auto-archival:\n\n# Run on the 1st of every month at 03:00\n0 3 1 * * cd /path/to/workspace && python3 scripts/memory_lifecycle_manager.py"
      },
      {
        "title": "Customization",
        "body": "Archive threshold: Edit ARCHIVE_THRESHOLD_DAYS in memory_lifecycle_manager.py (default: 180 days)\nQuery patterns: Add new regex patterns to QUERY_TYPES in memory_retrieval_strategy.py\nMemory directories: Add new modules to MODULES_TO_ARCHIVE in memory_lifecycle_manager.py\nTag categories: Tags are freeform — just use [category:value] in any .md file"
      },
      {
        "title": "Requirements",
        "body": "Python 3.8+\nNo external dependencies (stdlib only)"
      }
    ],
    "body": "Enhanced Memory\n\nA structured memory system that gives your OpenClaw agent organized, searchable, long-lived memory instead of a single monolithic MEMORY.md.\n\nWhy?\n\nThe default MEMORY.md approach hits a wall fast:\n\nOne file grows endlessly → slow to read, expensive on tokens\nNo categorization → food logs mixed with project notes mixed with relationship context\nNo retrieval strategy → agent re-reads everything or misses what matters\nNo lifecycle → old entries clutter active memory forever\n\nTagged Memory fixes all of this.\n\nCore Features\n1. Hierarchical Directory Organization\n\nMemories are stored in purpose-built directories:\n\nmemory/\n├── current/          # Active memories (last 6 months)\n├── archived/         # Auto-archived older memories (permanent, never deleted)\n│   └── YYYY-MM/      # Organized by month\n├── RELATION/         # One file per person (relationship context)\n├── food/             # Meal and food logs\n├── training/         # Exercise and workout records\n├── connections.md    # Global relationship graph\n├── system/           # System config and logs\n└── misc/             # Everything else\n\n2. Tag-Based Indexing\n\nTag any line in any memory file with [category:value] markers:\n\n## 2026-02-20\n\n- Had lunch with Zhang Hao [人物:张浩东] [类型:聚餐] [地点:campus]\n- Discussed the new project deadline [项目:openclaw] [类型:会议]\n- Yoyo learned a new trick today [宠物:悠悠] [类型:milestone]\n\n\nTags support multi-tag AND search — find the exact memory you need:\n\n# Single tag search\npython3 scripts/memory_tag_search.py \"人物:张浩东\"\n\n# Multi-tag AND search (all tags must match)\npython3 scripts/memory_tag_search.py \"人物:王隆哲\" \"类型:开票信息\"\n\n# List all tags in the system\npython3 scripts/memory_tag_search.py --list-tags\n\n# List tags under a specific category\npython3 scripts/memory_tag_search.py --list-tags --category 人物\n\n3. Lifecycle Management\n\nMemories age gracefully — never lost, always accessible:\n\nAge\tLocation\tStatus\n0–6 months\tmemory/current/\tActive, auto-retrieved\n6–12 months\tmemory/archived/YYYY-MM/\tArchived, searchable on demand\n12+ months\tmemory/archived/\tPermanent archive, manual query\n\nRun the lifecycle manager manually or via cron:\n\n# Default: archive memories older than 6 months\npython3 scripts/memory_lifecycle_manager.py\n\n# Custom threshold (e.g., 90 days)\npython3 scripts/memory_lifecycle_manager.py 90\n\n4. Smart Cross-Category Retrieval\n\nThe retrieval strategy script auto-classifies queries and searches the right directories:\n\npython3 scripts/memory_retrieval_strategy.py \"What did I eat yesterday?\"\n# → Searches memory/food/ + memory/current/\n\npython3 scripts/memory_retrieval_strategy.py \"How is Yoyo doing?\"\n# → Searches memory/RELATION/悠悠.md + memory/connections.md\n\npython3 scripts/memory_retrieval_strategy.py \"Yang Lingxiao\"\n# → Searches memory/RELATION/ + memory/connections.md\n\n\nQuery type detection covers: food, training, relationships, pets, system, mood, projects, and more.\n\nScripts\nScript\tPurpose\nscripts/memory_tag_search.py\tTag-based indexing and search (single/multi-tag AND queries, tag listing)\nscripts/memory_retrieval_strategy.py\tSmart retrieval — auto-classifies queries and routes to relevant memory directories\nscripts/memory_lifecycle_manager.py\tAutomatic archival of old memories (configurable threshold, never deletes)\nIntegration\nAGENTS.md\n\nAdd the following to your AGENTS.md memory section:\n\n## Memory\n\n### Directory Structure\n- `memory/current/` — active memories (6 months)\n- `memory/archived/` — permanent archive\n- `memory/RELATION/` — per-person relationship files\n- `memory/food/` — meal logs\n- `memory/training/` — workout logs\n\n### Retrieval Strategy\n- Exact queries (names, dates, codes) → `grep` the file system\n- Fuzzy/semantic queries → `python3 scripts/memory_retrieval_strategy.py \"<query>\"`\n- Tag search → `python3 scripts/memory_tag_search.py \"<category>:<value>\"`\n\n### Tagging Convention\nWhen writing memory entries, tag important lines:\n  [人物:name] [类型:type] [地点:place] [项目:project] [情绪:mood]\n\nHEARTBEAT.md\n\nAdd periodic memory maintenance to your heartbeat checklist:\n\n## Memory Maintenance (every few days)\n- [ ] Run `python3 scripts/memory_lifecycle_manager.py` to archive old memories\n- [ ] Run `python3 scripts/memory_tag_search.py --list-tags` to review tag health\n- [ ] Check `memory/current/` file count — if growing large, verify archival is running\n\nCron (optional)\n\nSet up monthly auto-archival:\n\n# Run on the 1st of every month at 03:00\n0 3 1 * * cd /path/to/workspace && python3 scripts/memory_lifecycle_manager.py\n\nCustomization\nArchive threshold: Edit ARCHIVE_THRESHOLD_DAYS in memory_lifecycle_manager.py (default: 180 days)\nQuery patterns: Add new regex patterns to QUERY_TYPES in memory_retrieval_strategy.py\nMemory directories: Add new modules to MODULES_TO_ARCHIVE in memory_lifecycle_manager.py\nTag categories: Tags are freeform — just use [category:value] in any .md file\nRequirements\nPython 3.8+\nNo external dependencies (stdlib only)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/fatcatMaoFei/openclaw-enhanced-memory",
    "publisherUrl": "https://clawhub.ai/fatcatMaoFei/openclaw-enhanced-memory",
    "owner": "fatcatMaoFei",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-enhanced-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-enhanced-memory",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-enhanced-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-enhanced-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-enhanced-memory/agent.md"
  }
}