{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vector-memory",
    "name": "vector-memory",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/BluePointDigital/vector-memory",
    "canonicalUrl": "https://clawhub.ai/BluePointDigital/vector-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/vector-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vector-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "install.sh",
      "MEMORY_STRUCTURE.md",
      "CHANGELOG.md",
      "README.md",
      "AGENTS.md",
      "SKILL.md"
    ],
    "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/vector-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/vector-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/vector-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vector-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vector-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": "Vector Memory",
        "body": "Smart memory search that automatically selects the best method:\n\nVector search (semantic, high quality) when synced\nBuilt-in search (keyword, fast) as fallback\n\nZero configuration required. Works immediately after install."
      },
      {
        "title": "Install from ClawHub",
        "body": "npx clawhub install vector-memory\n\nDone! memory_search now works with automatic method selection."
      },
      {
        "title": "Optional: Sync for Better Results",
        "body": "node vector-memory/smart_memory.js --sync\n\nAfter sync, searches use neural embeddings for semantic understanding."
      },
      {
        "title": "Smart Selection",
        "body": "// Same call, automatic best method\nmemory_search(\"James principles values\") \n\n// If vector ready: finds \"autonomy, competence, creation\" (semantic match)\n// If not ready: uses keyword search (fallback)"
      },
      {
        "title": "Behavior Flow",
        "body": "Check: Is vector index ready?\nYes: Use semantic search (synonyms, concepts)\nNo: Use built-in search (keywords)\nVector fails: Automatically fall back"
      },
      {
        "title": "memory_search",
        "body": "Auto-selects best method\n\nParameters:\n\nquery (string): Search query\nmax_results (number): Max results (default: 5)\n\nReturns: Matches with path, lines, score, snippet"
      },
      {
        "title": "memory_get",
        "body": "Get full content from file."
      },
      {
        "title": "memory_sync",
        "body": "Index memory files for vector search. Run after edits."
      },
      {
        "title": "memory_status",
        "body": "Check which method is active."
      },
      {
        "title": "Comparison",
        "body": "FeatureBuilt-inVectorSmart WrapperSynonyms❌✅✅ (when ready)SetupBuilt-inRequires sync✅ Zero configFallbackN/AManual✅ Automatic"
      },
      {
        "title": "Usage",
        "body": "Immediate (no action needed):\n\nnode vector-memory/smart_memory.js --search \"query\"\n\nBetter quality (after sync):\n\n# One-time setup\nnode vector-memory/smart_memory.js --sync\n\n# Now all searches use vector\nnode vector-memory/smart_memory.js --search \"query\""
      },
      {
        "title": "Files",
        "body": "FilePurposesmart_memory.jsMain entry - auto-selects methodvector_memory_local.jsVector implementationmemory.jsOpenClaw wrapper"
      },
      {
        "title": "Configuration",
        "body": "None required.\n\nOptional environment variables:\n\nexport MEMORY_DIR=/path/to/memory\nexport MEMORY_FILE=/path/to/MEMORY.md"
      },
      {
        "title": "Scaling",
        "body": "< 1000 chunks: Built-in + JSON (current)\n> 1000 chunks: Use pgvector (see references/pgvector.md)"
      },
      {
        "title": "References",
        "body": "Integration - Detailed setup\npgvector - Large-scale deployment"
      }
    ],
    "body": "Vector Memory\n\nSmart memory search that automatically selects the best method:\n\nVector search (semantic, high quality) when synced\nBuilt-in search (keyword, fast) as fallback\n\nZero configuration required. Works immediately after install.\n\nQuick Start\nInstall from ClawHub\nnpx clawhub install vector-memory\n\n\nDone! memory_search now works with automatic method selection.\n\nOptional: Sync for Better Results\nnode vector-memory/smart_memory.js --sync\n\n\nAfter sync, searches use neural embeddings for semantic understanding.\n\nHow It Works\nSmart Selection\n// Same call, automatic best method\nmemory_search(\"James principles values\") \n\n// If vector ready: finds \"autonomy, competence, creation\" (semantic match)\n// If not ready: uses keyword search (fallback)\n\nBehavior Flow\nCheck: Is vector index ready?\nYes: Use semantic search (synonyms, concepts)\nNo: Use built-in search (keywords)\nVector fails: Automatically fall back\nTools\nmemory_search\n\nAuto-selects best method\n\nParameters:\n\nquery (string): Search query\nmax_results (number): Max results (default: 5)\n\nReturns: Matches with path, lines, score, snippet\n\nmemory_get\n\nGet full content from file.\n\nmemory_sync\n\nIndex memory files for vector search. Run after edits.\n\nmemory_status\n\nCheck which method is active.\n\nComparison\nFeature\tBuilt-in\tVector\tSmart Wrapper\nSynonyms\t❌\t✅\t✅ (when ready)\nSetup\tBuilt-in\tRequires sync\t✅ Zero config\nFallback\tN/A\tManual\t✅ Automatic\nUsage\n\nImmediate (no action needed):\n\nnode vector-memory/smart_memory.js --search \"query\"\n\n\nBetter quality (after sync):\n\n# One-time setup\nnode vector-memory/smart_memory.js --sync\n\n# Now all searches use vector\nnode vector-memory/smart_memory.js --search \"query\"\n\nFiles\nFile\tPurpose\nsmart_memory.js\tMain entry - auto-selects method\nvector_memory_local.js\tVector implementation\nmemory.js\tOpenClaw wrapper\nConfiguration\n\nNone required.\n\nOptional environment variables:\n\nexport MEMORY_DIR=/path/to/memory\nexport MEMORY_FILE=/path/to/MEMORY.md\n\nScaling\n< 1000 chunks: Built-in + JSON (current)\n> 1000 chunks: Use pgvector (see references/pgvector.md)\nReferences\nIntegration - Detailed setup\npgvector - Large-scale deployment"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/BluePointDigital/vector-memory",
    "publisherUrl": "https://clawhub.ai/BluePointDigital/vector-memory",
    "owner": "BluePointDigital",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vector-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/vector-memory",
    "agentUrl": "https://openagent3.xyz/skills/vector-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vector-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vector-memory/agent.md"
  }
}