{
  "schemaVersion": "1.0",
  "item": {
    "slug": "qmd-memory",
    "name": "QMD Memory",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/asabovetech/qmd-memory",
    "canonicalUrl": "https://clawhub.ai/asabovetech/qmd-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/qmd-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qmd-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "scripts/calculate-savings.sh",
      "scripts/refresh.sh",
      "scripts/serve.sh",
      "scripts/setup.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/qmd-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/qmd-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/qmd-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qmd-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qmd-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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Local Hybrid Search — Save $50-300/month in API Costs",
        "body": "Author: As Above Technologies\nVersion: 1.0.0\nClawHub: [Coming Soon]"
      },
      {
        "title": "API Costs You're Paying Now",
        "body": "OperationAPI CostFrequencyMonthly Costmemory_search (embedding)$0.02-0.0550-200/day$30-300Context retrieval$0.01-0.03100+/day$30-90Semantic queries$0.03-0.0820-50/day$18-120TOTAL$78-510/month"
      },
      {
        "title": "With QMD Local",
        "body": "OperationCostWhyAll searches$0Runs on your machineEmbeddings$0Local GGUF modelsRe-ranking$0Local LLM\n\nYour savings: $50-300+/month\n\nOne-time setup. Forever free searches."
      },
      {
        "title": "🚀 QUICK START",
        "body": "# Install the skill\nclawhub install asabove/qmd-memory\n\n# Run setup (installs QMD, configures collections)\nopenclaw skill run qmd-memory setup\n\n# That's it. Your memory is now supercharged."
      },
      {
        "title": "1. Automatic Collection Setup",
        "body": "Based on your workspace structure, we create optimized collections:\n\n✓ workspace     — Core agent files (MEMORY.md, SOUL.md, etc.)\n✓ daily-logs    — memory/*.md daily logs\n✓ intelligence  — intelligence/*.md (if exists)\n✓ projects      — projects/**/*.md (if exists)\n✓ documents     — Any additional doc folders you specify"
      },
      {
        "title": "2. Smart Context Descriptions",
        "body": "We add context to each collection so QMD understands what's where:\n\nqmd://workspace    → \"Agent identity and configuration files\"\nqmd://daily-logs   → \"Daily work logs and session history\"\nqmd://intelligence → \"Analysis, research, and reference documents\""
      },
      {
        "title": "3. Pre-configured Cron Jobs",
        "body": "# Auto-update index (nightly at 3am)\n0 3 * * * qmd update && qmd embed\n\n# Keep your memory fresh without thinking about it"
      },
      {
        "title": "4. OpenClaw Integration",
        "body": "Memory search now uses QMD automatically:\n\nmemory_search → routes to QMD hybrid search\nmemory_get → retrieves from QMD collections\nResults include collection context"
      },
      {
        "title": "5. Multi-Agent MCP Server (Optional)",
        "body": "# Start shared memory server\nopenclaw skill run qmd-memory serve\n\n# All your agents can now query collective memory\n# Forge, Thoth, Axis — shared knowledge base"
      },
      {
        "title": "📊 SEARCH MODES",
        "body": "ModeCommandBest ForKeywordqmd search \"query\"Exact matches, fastSemanticqmd vsearch \"query\"Conceptual similarityHybridqmd query \"query\"Best quality (recommended)"
      },
      {
        "title": "Example Queries",
        "body": "# Find exact mentions\nqmd search \"Charlene\" -n 5\n\n# Find conceptually related content\nqmd vsearch \"how should we handle customer complaints\"\n\n# Best quality — expansion + reranking\nqmd query \"what decisions did we make about pricing strategy\"\n\n# Search specific collection\nqmd search \"API keys\" -c workspace"
      },
      {
        "title": "Add Custom Collections",
        "body": "openclaw skill run qmd-memory add-collection ~/Documents/research --name research"
      },
      {
        "title": "Add Context",
        "body": "openclaw skill run qmd-memory add-context qmd://research \"Market research and competitive analysis\""
      },
      {
        "title": "Refresh Index",
        "body": "openclaw skill run qmd-memory refresh"
      },
      {
        "title": "Trading/Investing Workspace",
        "body": "openclaw skill run qmd-memory template trading\n\nCreates:\n\nintelligence — Trading systems, dashboards, signals\nmarket-data — Price history, analysis\nresearch — Due diligence, reports\ndaily-logs — Trade journal"
      },
      {
        "title": "Content Creator Workspace",
        "body": "openclaw skill run qmd-memory template content\n\nCreates:\n\narticles — Published content\ndrafts — Work in progress\nresearch — Source material\nideas — Brainstorms, notes"
      },
      {
        "title": "Developer Workspace",
        "body": "openclaw skill run qmd-memory template developer\n\nCreates:\n\ndocs — Documentation\nnotes — Technical notes\ndecisions — ADRs, architecture decisions\nsnippets — Code snippets, examples"
      },
      {
        "title": "📈 COST SAVINGS CALCULATOR",
        "body": "Run this to see your estimated savings:\n\nopenclaw skill run qmd-memory calculate-savings\n\nOutput:\n\nYour Current API Memory Costs (estimated):\n  memory_search calls/day:     ~75\n  Average cost per call:       $0.03\n  Monthly API cost:            $67.50\n\nWith QMD Local:\n  Monthly cost:                $0.00\n\nYOUR MONTHLY SAVINGS:          $67.50\nYOUR ANNUAL SAVINGS:           $810.00\n\nROI on skill purchase:         40x (if skill was $20)"
      },
      {
        "title": "Models Used (Auto-Downloaded)",
        "body": "ModelPurposeSizeembeddinggemma-300M-Q8_0Vector embeddings~300MBqwen3-reranker-0.6b-q8_0Re-ranking results~640MBqmd-query-expansion-1.7B-q4_k_mQuery expansion~1.1GB\n\nTotal: ~2GB (one-time download)"
      },
      {
        "title": "System Requirements",
        "body": "Node.js >= 22\n~3GB disk space (models + index)\n~2GB RAM during embedding (then minimal)"
      },
      {
        "title": "Where Data is Stored",
        "body": "~/.cache/qmd/\n├── index.sqlite      # Search index\n├── models/           # GGUF models\n└── mcp.pid           # MCP server PID (if running)"
      },
      {
        "title": "🤝 SUPPORT",
        "body": "Questions?\n\nGitHub Issues: github.com/asabove/qmd-memory-skill\nDiscord: As Above community\nEmail: support@asabove.tech\n\nFound it valuable?\n\nStar us on ClawHub\nShare with other OpenClaw users\nSubscribe to our newsletter for more agent optimization tips"
      },
      {
        "title": "📜 LICENSE",
        "body": "MIT — Use freely, modify as needed.\n\nQMD itself is created by Tobi Lütke (github.com/tobi/qmd).\nThis skill provides easy OpenClaw integration.\n\n\"Stop paying for memory. Start compounding knowledge.\"\n\nAs Above Technologies — Agent Infrastructure for Humans"
      }
    ],
    "body": "QMD Memory Skill for OpenClaw\nLocal Hybrid Search — Save $50-300/month in API Costs\n\nAuthor: As Above Technologies Version: 1.0.0 ClawHub: [Coming Soon]\n\n💰 THE VALUE PROPOSITION\nAPI Costs You're Paying Now\nOperation\tAPI Cost\tFrequency\tMonthly Cost\nmemory_search (embedding)\t$0.02-0.05\t50-200/day\t$30-300\nContext retrieval\t$0.01-0.03\t100+/day\t$30-90\nSemantic queries\t$0.03-0.08\t20-50/day\t$18-120\nTOTAL\t\t\t$78-510/month\nWith QMD Local\nOperation\tCost\tWhy\nAll searches\t$0\tRuns on your machine\nEmbeddings\t$0\tLocal GGUF models\nRe-ranking\t$0\tLocal LLM\n\nYour savings: $50-300+/month\n\nOne-time setup. Forever free searches.\n\n🚀 QUICK START\n# Install the skill\nclawhub install asabove/qmd-memory\n\n# Run setup (installs QMD, configures collections)\nopenclaw skill run qmd-memory setup\n\n# That's it. Your memory is now supercharged.\n\nWHAT YOU GET\n1. Automatic Collection Setup\n\nBased on your workspace structure, we create optimized collections:\n\n✓ workspace     — Core agent files (MEMORY.md, SOUL.md, etc.)\n✓ daily-logs    — memory/*.md daily logs\n✓ intelligence  — intelligence/*.md (if exists)\n✓ projects      — projects/**/*.md (if exists)\n✓ documents     — Any additional doc folders you specify\n\n2. Smart Context Descriptions\n\nWe add context to each collection so QMD understands what's where:\n\nqmd://workspace    → \"Agent identity and configuration files\"\nqmd://daily-logs   → \"Daily work logs and session history\"\nqmd://intelligence → \"Analysis, research, and reference documents\"\n\n3. Pre-configured Cron Jobs\n# Auto-update index (nightly at 3am)\n0 3 * * * qmd update && qmd embed\n\n# Keep your memory fresh without thinking about it\n\n4. OpenClaw Integration\n\nMemory search now uses QMD automatically:\n\nmemory_search → routes to QMD hybrid search\nmemory_get → retrieves from QMD collections\nResults include collection context\n5. Multi-Agent MCP Server (Optional)\n# Start shared memory server\nopenclaw skill run qmd-memory serve\n\n# All your agents can now query collective memory\n# Forge, Thoth, Axis — shared knowledge base\n\n📊 SEARCH MODES\nMode\tCommand\tBest For\nKeyword\tqmd search \"query\"\tExact matches, fast\nSemantic\tqmd vsearch \"query\"\tConceptual similarity\nHybrid\tqmd query \"query\"\tBest quality (recommended)\nExample Queries\n# Find exact mentions\nqmd search \"Charlene\" -n 5\n\n# Find conceptually related content\nqmd vsearch \"how should we handle customer complaints\"\n\n# Best quality — expansion + reranking\nqmd query \"what decisions did we make about pricing strategy\"\n\n# Search specific collection\nqmd search \"API keys\" -c workspace\n\n🔧 CONFIGURATION\nAdd Custom Collections\nopenclaw skill run qmd-memory add-collection ~/Documents/research --name research\n\nAdd Context\nopenclaw skill run qmd-memory add-context qmd://research \"Market research and competitive analysis\"\n\nRefresh Index\nopenclaw skill run qmd-memory refresh\n\n💡 TEMPLATES\nTrading/Investing Workspace\nopenclaw skill run qmd-memory template trading\n\n\nCreates:\n\nintelligence — Trading systems, dashboards, signals\nmarket-data — Price history, analysis\nresearch — Due diligence, reports\ndaily-logs — Trade journal\nContent Creator Workspace\nopenclaw skill run qmd-memory template content\n\n\nCreates:\n\narticles — Published content\ndrafts — Work in progress\nresearch — Source material\nideas — Brainstorms, notes\nDeveloper Workspace\nopenclaw skill run qmd-memory template developer\n\n\nCreates:\n\ndocs — Documentation\nnotes — Technical notes\ndecisions — ADRs, architecture decisions\nsnippets — Code snippets, examples\n📈 COST SAVINGS CALCULATOR\n\nRun this to see your estimated savings:\n\nopenclaw skill run qmd-memory calculate-savings\n\n\nOutput:\n\nYour Current API Memory Costs (estimated):\n  memory_search calls/day:     ~75\n  Average cost per call:       $0.03\n  Monthly API cost:            $67.50\n\nWith QMD Local:\n  Monthly cost:                $0.00\n\nYOUR MONTHLY SAVINGS:          $67.50\nYOUR ANNUAL SAVINGS:           $810.00\n\nROI on skill purchase:         40x (if skill was $20)\n\n🛠️ TECHNICAL DETAILS\nModels Used (Auto-Downloaded)\nModel\tPurpose\tSize\nembeddinggemma-300M-Q8_0\tVector embeddings\t~300MB\nqwen3-reranker-0.6b-q8_0\tRe-ranking results\t~640MB\nqmd-query-expansion-1.7B-q4_k_m\tQuery expansion\t~1.1GB\n\nTotal: ~2GB (one-time download)\n\nSystem Requirements\nNode.js >= 22\n~3GB disk space (models + index)\n~2GB RAM during embedding (then minimal)\nWhere Data is Stored\n~/.cache/qmd/\n├── index.sqlite      # Search index\n├── models/           # GGUF models\n└── mcp.pid           # MCP server PID (if running)\n\n🤝 SUPPORT\n\nQuestions?\n\nGitHub Issues: github.com/asabove/qmd-memory-skill\nDiscord: As Above community\nEmail: support@asabove.tech\n\nFound it valuable?\n\nStar us on ClawHub\nShare with other OpenClaw users\nSubscribe to our newsletter for more agent optimization tips\n📜 LICENSE\n\nMIT — Use freely, modify as needed.\n\nQMD itself is created by Tobi Lütke (github.com/tobi/qmd). This skill provides easy OpenClaw integration.\n\n\"Stop paying for memory. Start compounding knowledge.\"\n\nAs Above Technologies — Agent Infrastructure for Humans"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/asabovetech/qmd-memory",
    "publisherUrl": "https://clawhub.ai/asabovetech/qmd-memory",
    "owner": "asabovetech",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/qmd-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/qmd-memory",
    "agentUrl": "https://openagent3.xyz/skills/qmd-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qmd-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qmd-memory/agent.md"
  }
}