{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-memory-enhancer",
    "name": "Openclaw Memory Enhancer",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/henryfcb/openclaw-memory-enhancer",
    "canonicalUrl": "https://clawhub.ai/henryfcb/openclaw-memory-enhancer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-memory-enhancer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-memory-enhancer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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. 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-memory-enhancer"
    },
    "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-memory-enhancer",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer/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": "🧠 OpenClaw Memory Enhancer",
        "body": "Give OpenClaw long-term memory - remember important information across sessions and automatically recall relevant context for conversations."
      },
      {
        "title": "Core Capabilities",
        "body": "CapabilityDescription🔍 Semantic SearchVector similarity search, understanding intent not just keywords📂 Auto LoadAutomatically reads all files from memory/ directory💡 Smart RecallFinds relevant historical memory during conversations🔗 Memory GraphBuilds connections between related memories💾 Local Storage100% local, no cloud, complete privacy🚀 Edge Optimized<10MB memory, runs on Jetson/Raspberry Pi"
      },
      {
        "title": "Quick Reference",
        "body": "TaskCommand (Edge Version)Command (Standard Version)Load memoriespython3 memory_enhancer_edge.py --loadpython3 memory_enhancer.py --loadSearch--search \"query\"--search \"query\"Add memory--add \"content\"--add \"content\"Export--export--exportStats--stats--stats"
      },
      {
        "title": "When to Use",
        "body": "Use this skill when:\n\nYou want OpenClaw to remember things across sessions\nYou need to build a knowledge base from chat history\nYou're working on long-term projects that need context\nYou want automatic FAQ generation from conversations\nYou're running on edge devices with limited memory\n\nDon't use when:\n\nSimple note-taking apps are sufficient\nYou don't need cross-session memory\nYou have plenty of memory and want maximum accuracy (use standard version)"
      },
      {
        "title": "Edge Version ⭐ Recommended",
        "body": "Best for: Jetson, Raspberry Pi, embedded devices\n\npython3 memory_enhancer_edge.py --load\n\nFeatures:\n\nZero dependencies (Python stdlib only)\nMemory usage < 10MB\nLightweight keyword + vector matching\nPerfect for resource-constrained devices"
      },
      {
        "title": "Standard Version",
        "body": "Best for: Desktop/server, maximum accuracy\n\npip install sentence-transformers numpy\npython3 memory_enhancer.py --load\n\nFeatures:\n\nUses sentence-transformers for high-quality embeddings\nBetter semantic understanding\nMemory usage 50-100MB\nRequires model download (~50MB)"
      },
      {
        "title": "Via ClawHub (Recommended)",
        "body": "clawhub install openclaw-memory-enhancer"
      },
      {
        "title": "Via Git",
        "body": "git clone https://github.com/henryfcb/openclaw-memory-enhancer.git \\\n  ~/.openclaw/skills/openclaw-memory-enhancer"
      },
      {
        "title": "Command Line",
        "body": "# Load existing OpenClaw memories\ncd ~/.openclaw/skills/openclaw-memory-enhancer\npython3 memory_enhancer_edge.py --load\n\n# Search for memories\npython3 memory_enhancer_edge.py --search \"voice-call plugin setup\"\n\n# Add a new memory\npython3 memory_enhancer_edge.py --add \"User prefers dark mode\"\n\n# Show statistics\npython3 memory_enhancer_edge.py --stats\n\n# Export to Markdown\npython3 memory_enhancer_edge.py --export"
      },
      {
        "title": "Python API",
        "body": "from memory_enhancer_edge import MemoryEnhancerEdge\n\n# Initialize\nmemory = MemoryEnhancerEdge()\n\n# Load existing memories\nmemory.load_openclaw_memory()\n\n# Search for relevant memories\nresults = memory.search_memory(\"AI trends report\", top_k=3)\nfor r in results:\n    print(f\"[{r['similarity']:.2f}] {r['content'][:100]}...\")\n\n# Recall context for a conversation\ncontext = memory.recall_for_prompt(\"Help me check billing\")\n# Returns formatted memory context\n\n# Add new memory\nmemory.add_memory(\n    content=\"User prefers direct results\",\n    source=\"chat\",\n    memory_type=\"preference\"\n)"
      },
      {
        "title": "OpenClaw Integration",
        "body": "# In your OpenClaw agent\nfrom skills.openclaw_memory_enhancer.memory_enhancer_edge import MemoryEnhancerEdge\n\nclass EnhancedAgent:\n    def __init__(self):\n        self.memory = MemoryEnhancerEdge()\n        self.memory.load_openclaw_memory()\n    \n    def process(self, user_input: str) -> str:\n        # 1. Recall relevant memories\n        memory_context = self.memory.recall_for_prompt(user_input)\n        \n        # 2. Enhance prompt with context\n        enhanced_prompt = f\"\"\"\n{memory_context}\n\nUser: {user_input}\n\"\"\"\n        \n        # 3. Call LLM with enhanced context\n        response = call_llm(enhanced_prompt)\n        \n        return response"
      },
      {
        "title": "Memory Types",
        "body": "TypeDescriptionExampledaily_logDaily memory filesmemory/2026-02-22.mdcapabilityCapability recordsSkills, toolscore_memoryCore conventionsImportant rulesqaQuestion & AnswerQ: How to... A: You should...instructionDirect instructions\"Remember: always do X\"solutionTechnical solutionsStep-by-step guidespreferenceUser preferences\"User likes dark mode\""
      },
      {
        "title": "Memory Encoding (Edge Version)",
        "body": "Keyword Extraction: Extract important words from text\nHash Vector: Map keywords to vector positions\nNormalization: L2 normalize the vector\nStorage: Save to local JSON file"
      },
      {
        "title": "Memory Retrieval",
        "body": "Query Encoding: Convert query to same vector format\nKeyword Pre-filter: Fast filter by common keywords\nSimilarity Calculation: Cosine similarity between vectors\nRanking: Return top-k most similar memories"
      },
      {
        "title": "Privacy Protection",
        "body": "All data stored locally in ~/.openclaw/workspace/knowledge-base/\nNo network requests\nNo external API calls\nNo data leaves your device"
      },
      {
        "title": "Edge Version",
        "body": "Vector Dimensions: 128\nMemory Usage: < 10MB\nDependencies: None (Python stdlib)\nStorage Format: JSON\nMax Memories: 1000 (configurable)\nQuery Latency: < 100ms"
      },
      {
        "title": "Standard Version",
        "body": "Vector Dimensions: 384\nMemory Usage: 50-100MB\nDependencies: sentence-transformers, numpy\nStorage Format: NumPy + JSON\nModel Size: ~50MB download\nQuery Latency: < 50ms"
      },
      {
        "title": "Configuration",
        "body": "Edit these parameters in the code:\n\nself.config = {\n    \"vector_dim\": 128,        # Vector dimensions\n    \"max_memory_size\": 1000,  # Max number of memories\n    \"chunk_size\": 500,        # Content chunk size\n    \"min_keyword_len\": 2,     # Minimum keyword length\n}"
      },
      {
        "title": "No results found",
        "body": "# Lower the threshold\nresults = memory.search_memory(query, threshold=0.2)  # Default 0.3\n\n# Increase top_k\nresults = memory.search_memory(query, top_k=10)  # Default 5"
      },
      {
        "title": "Memory limit reached",
        "body": "The system automatically removes oldest memories when limit is reached.\n\nTo increase limit:\n\nself.config[\"max_memory_size\"] = 5000  # Increase from 1000"
      },
      {
        "title": "Slow performance",
        "body": "Use Edge version instead of Standard\nReduce max_memory_size\nUse keyword pre-filtering (automatic)"
      },
      {
        "title": "Contributing",
        "body": "Fork the repository\nCreate a feature branch\nMake your changes\nSubmit a Pull Request"
      },
      {
        "title": "License",
        "body": "MIT License - See LICENSE file for details."
      },
      {
        "title": "Acknowledgments",
        "body": "Built for the OpenClaw ecosystem\nOptimized for edge computing devices\nInspired by long-term memory systems in AI\n\nNot an official OpenClaw or Moonshot AI product.\n\nUsers must provide their own OpenClaw workspace and API keys."
      }
    ],
    "body": "🧠 OpenClaw Memory Enhancer\n\nGive OpenClaw long-term memory - remember important information across sessions and automatically recall relevant context for conversations.\n\nCore Capabilities\nCapability\tDescription\n🔍 Semantic Search\tVector similarity search, understanding intent not just keywords\n📂 Auto Load\tAutomatically reads all files from memory/ directory\n💡 Smart Recall\tFinds relevant historical memory during conversations\n🔗 Memory Graph\tBuilds connections between related memories\n💾 Local Storage\t100% local, no cloud, complete privacy\n🚀 Edge Optimized\t<10MB memory, runs on Jetson/Raspberry Pi\nQuick Reference\nTask\tCommand (Edge Version)\tCommand (Standard Version)\nLoad memories\tpython3 memory_enhancer_edge.py --load\tpython3 memory_enhancer.py --load\nSearch\t--search \"query\"\t--search \"query\"\nAdd memory\t--add \"content\"\t--add \"content\"\nExport\t--export\t--export\nStats\t--stats\t--stats\nWhen to Use\n\nUse this skill when:\n\nYou want OpenClaw to remember things across sessions\nYou need to build a knowledge base from chat history\nYou're working on long-term projects that need context\nYou want automatic FAQ generation from conversations\nYou're running on edge devices with limited memory\n\nDon't use when:\n\nSimple note-taking apps are sufficient\nYou don't need cross-session memory\nYou have plenty of memory and want maximum accuracy (use standard version)\nVersions\nEdge Version ⭐ Recommended\n\nBest for: Jetson, Raspberry Pi, embedded devices\n\npython3 memory_enhancer_edge.py --load\n\n\nFeatures:\n\nZero dependencies (Python stdlib only)\nMemory usage < 10MB\nLightweight keyword + vector matching\nPerfect for resource-constrained devices\nStandard Version\n\nBest for: Desktop/server, maximum accuracy\n\npip install sentence-transformers numpy\npython3 memory_enhancer.py --load\n\n\nFeatures:\n\nUses sentence-transformers for high-quality embeddings\nBetter semantic understanding\nMemory usage 50-100MB\nRequires model download (~50MB)\nInstallation\nVia ClawHub (Recommended)\nclawhub install openclaw-memory-enhancer\n\nVia Git\ngit clone https://github.com/henryfcb/openclaw-memory-enhancer.git \\\n  ~/.openclaw/skills/openclaw-memory-enhancer\n\nUsage Examples\nCommand Line\n# Load existing OpenClaw memories\ncd ~/.openclaw/skills/openclaw-memory-enhancer\npython3 memory_enhancer_edge.py --load\n\n# Search for memories\npython3 memory_enhancer_edge.py --search \"voice-call plugin setup\"\n\n# Add a new memory\npython3 memory_enhancer_edge.py --add \"User prefers dark mode\"\n\n# Show statistics\npython3 memory_enhancer_edge.py --stats\n\n# Export to Markdown\npython3 memory_enhancer_edge.py --export\n\nPython API\nfrom memory_enhancer_edge import MemoryEnhancerEdge\n\n# Initialize\nmemory = MemoryEnhancerEdge()\n\n# Load existing memories\nmemory.load_openclaw_memory()\n\n# Search for relevant memories\nresults = memory.search_memory(\"AI trends report\", top_k=3)\nfor r in results:\n    print(f\"[{r['similarity']:.2f}] {r['content'][:100]}...\")\n\n# Recall context for a conversation\ncontext = memory.recall_for_prompt(\"Help me check billing\")\n# Returns formatted memory context\n\n# Add new memory\nmemory.add_memory(\n    content=\"User prefers direct results\",\n    source=\"chat\",\n    memory_type=\"preference\"\n)\n\nOpenClaw Integration\n# In your OpenClaw agent\nfrom skills.openclaw_memory_enhancer.memory_enhancer_edge import MemoryEnhancerEdge\n\nclass EnhancedAgent:\n    def __init__(self):\n        self.memory = MemoryEnhancerEdge()\n        self.memory.load_openclaw_memory()\n    \n    def process(self, user_input: str) -> str:\n        # 1. Recall relevant memories\n        memory_context = self.memory.recall_for_prompt(user_input)\n        \n        # 2. Enhance prompt with context\n        enhanced_prompt = f\"\"\"\n{memory_context}\n\nUser: {user_input}\n\"\"\"\n        \n        # 3. Call LLM with enhanced context\n        response = call_llm(enhanced_prompt)\n        \n        return response\n\nMemory Types\nType\tDescription\tExample\ndaily_log\tDaily memory files\tmemory/2026-02-22.md\ncapability\tCapability records\tSkills, tools\ncore_memory\tCore conventions\tImportant rules\nqa\tQuestion & Answer\tQ: How to... A: You should...\ninstruction\tDirect instructions\t\"Remember: always do X\"\nsolution\tTechnical solutions\tStep-by-step guides\npreference\tUser preferences\t\"User likes dark mode\"\nHow It Works\nMemory Encoding (Edge Version)\nKeyword Extraction: Extract important words from text\nHash Vector: Map keywords to vector positions\nNormalization: L2 normalize the vector\nStorage: Save to local JSON file\nMemory Retrieval\nQuery Encoding: Convert query to same vector format\nKeyword Pre-filter: Fast filter by common keywords\nSimilarity Calculation: Cosine similarity between vectors\nRanking: Return top-k most similar memories\nPrivacy Protection\nAll data stored locally in ~/.openclaw/workspace/knowledge-base/\nNo network requests\nNo external API calls\nNo data leaves your device\nTechnical Specifications\nEdge Version\nVector Dimensions: 128\nMemory Usage: < 10MB\nDependencies: None (Python stdlib)\nStorage Format: JSON\nMax Memories: 1000 (configurable)\nQuery Latency: < 100ms\n\nStandard Version\nVector Dimensions: 384\nMemory Usage: 50-100MB\nDependencies: sentence-transformers, numpy\nStorage Format: NumPy + JSON\nModel Size: ~50MB download\nQuery Latency: < 50ms\n\nConfiguration\n\nEdit these parameters in the code:\n\nself.config = {\n    \"vector_dim\": 128,        # Vector dimensions\n    \"max_memory_size\": 1000,  # Max number of memories\n    \"chunk_size\": 500,        # Content chunk size\n    \"min_keyword_len\": 2,     # Minimum keyword length\n}\n\nTroubleshooting\nNo results found\n# Lower the threshold\nresults = memory.search_memory(query, threshold=0.2)  # Default 0.3\n\n# Increase top_k\nresults = memory.search_memory(query, top_k=10)  # Default 5\n\nMemory limit reached\n\nThe system automatically removes oldest memories when limit is reached.\n\nTo increase limit:\n\nself.config[\"max_memory_size\"] = 5000  # Increase from 1000\n\nSlow performance\nUse Edge version instead of Standard\nReduce max_memory_size\nUse keyword pre-filtering (automatic)\nContributing\nFork the repository\nCreate a feature branch\nMake your changes\nSubmit a Pull Request\nLicense\n\nMIT License - See LICENSE file for details.\n\nAcknowledgments\nBuilt for the OpenClaw ecosystem\nOptimized for edge computing devices\nInspired by long-term memory systems in AI\n\nNot an official OpenClaw or Moonshot AI product.\n\nUsers must provide their own OpenClaw workspace and API keys."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/henryfcb/openclaw-memory-enhancer",
    "publisherUrl": "https://clawhub.ai/henryfcb/openclaw-memory-enhancer",
    "owner": "henryfcb",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-memory-enhancer",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-memory-enhancer/agent.md"
  }
}