{
  "schemaVersion": "1.0",
  "item": {
    "slug": "memory-setup",
    "name": "Memory Setup",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jrbobbyhansen-pixel/memory-setup",
    "canonicalUrl": "https://clawhub.ai/jrbobbyhansen-pixel/memory-setup",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/memory-setup",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-setup",
    "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",
      "slug": "memory-setup",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-05T11:26:40.671Z",
      "expiresAt": "2026-05-12T11:26:40.671Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-setup",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-setup",
        "contentDisposition": "attachment; filename=\"memory-setup-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "memory-setup"
      },
      "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/memory-setup"
    },
    "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/memory-setup",
    "agentPageUrl": "https://openagent3.xyz/skills/memory-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-setup/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": "Memory Setup Skill",
        "body": "Transform your agent from goldfish to elephant. This skill helps configure persistent memory for Moltbot/Clawdbot."
      },
      {
        "title": "1. Enable Memory Search in Config",
        "body": "Add to ~/.clawdbot/clawdbot.json (or moltbot.json):\n\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"voyage\",\n    \"sources\": [\"memory\", \"sessions\"],\n    \"indexMode\": \"hot\",\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  }\n}"
      },
      {
        "title": "2. Create Memory Structure",
        "body": "In your workspace, create:\n\nworkspace/\n├── MEMORY.md              # Long-term curated memory\n└── memory/\n    ├── logs/              # Daily logs (YYYY-MM-DD.md)\n    ├── projects/          # Project-specific context\n    ├── groups/            # Group chat context\n    └── system/            # Preferences, setup notes"
      },
      {
        "title": "3. Initialize MEMORY.md",
        "body": "Create MEMORY.md in workspace root:\n\n# MEMORY.md — Long-Term Memory\n\n## About [User Name]\n- Key facts, preferences, context\n\n## Active Projects\n- Project summaries and status\n\n## Decisions & Lessons\n- Important choices made\n- Lessons learned\n\n## Preferences\n- Communication style\n- Tools and workflows"
      },
      {
        "title": "Config Options Explained",
        "body": "SettingPurposeRecommendedenabledTurn on memory searchtrueproviderEmbedding provider\"voyage\"sourcesWhat to index[\"memory\", \"sessions\"]indexModeWhen to index\"hot\" (real-time)minScoreRelevance threshold0.3 (lower = more results)maxResultsMax snippets returned20"
      },
      {
        "title": "Provider Options",
        "body": "voyage — Voyage AI embeddings (recommended)\nopenai — OpenAI embeddings\nlocal — Local embeddings (no API needed)"
      },
      {
        "title": "Source Options",
        "body": "memory — MEMORY.md + memory/*.md files\nsessions — Past conversation transcripts\nboth — Full context (recommended)"
      },
      {
        "title": "Daily Log Format",
        "body": "Create memory/logs/YYYY-MM-DD.md daily:\n\n# YYYY-MM-DD — Daily Log\n\n## [Time] — [Event/Task]\n- What happened\n- Decisions made\n- Follow-ups needed\n\n## [Time] — [Another Event]\n- Details"
      },
      {
        "title": "Agent Instructions (AGENTS.md)",
        "body": "Add to your AGENTS.md for agent behavior:\n\n## Memory Recall\nBefore answering questions about prior work, decisions, dates, people, preferences, or todos:\n1. Run memory_search with relevant query\n2. Use memory_get to pull specific lines if needed\n3. If low confidence after search, say you checked"
      },
      {
        "title": "Memory search not working?",
        "body": "Check memorySearch.enabled: true in config\nVerify MEMORY.md exists in workspace root\nRestart gateway: clawdbot gateway restart"
      },
      {
        "title": "Results not relevant?",
        "body": "Lower minScore to 0.2 for more results\nIncrease maxResults to 30\nCheck that memory files have meaningful content"
      },
      {
        "title": "Provider errors?",
        "body": "Voyage: Set VOYAGE_API_KEY in environment\nOpenAI: Set OPENAI_API_KEY in environment\nUse local provider if no API keys available"
      },
      {
        "title": "Verification",
        "body": "Test memory is working:\n\nUser: \"What do you remember about [past topic]?\"\nAgent: [Should search memory and return relevant context]\n\nIf agent has no memory, config isn't applied. Restart gateway."
      },
      {
        "title": "Full Config Example",
        "body": "{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"voyage\",\n    \"sources\": [\"memory\", \"sessions\"],\n    \"indexMode\": \"hot\",\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  },\n  \"workspace\": \"/path/to/your/workspace\"\n}"
      },
      {
        "title": "Why This Matters",
        "body": "Without memory:\n\nAgent forgets everything between sessions\nRepeats questions, loses context\nNo continuity on projects\n\nWith memory:\n\nRecalls past conversations\nKnows your preferences\nTracks project history\nBuilds relationship over time\n\nGoldfish → Elephant. 🐘"
      }
    ],
    "body": "Memory Setup Skill\n\nTransform your agent from goldfish to elephant. This skill helps configure persistent memory for Moltbot/Clawdbot.\n\nQuick Setup\n1. Enable Memory Search in Config\n\nAdd to ~/.clawdbot/clawdbot.json (or moltbot.json):\n\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"voyage\",\n    \"sources\": [\"memory\", \"sessions\"],\n    \"indexMode\": \"hot\",\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  }\n}\n\n2. Create Memory Structure\n\nIn your workspace, create:\n\nworkspace/\n├── MEMORY.md              # Long-term curated memory\n└── memory/\n    ├── logs/              # Daily logs (YYYY-MM-DD.md)\n    ├── projects/          # Project-specific context\n    ├── groups/            # Group chat context\n    └── system/            # Preferences, setup notes\n\n3. Initialize MEMORY.md\n\nCreate MEMORY.md in workspace root:\n\n# MEMORY.md — Long-Term Memory\n\n## About [User Name]\n- Key facts, preferences, context\n\n## Active Projects\n- Project summaries and status\n\n## Decisions & Lessons\n- Important choices made\n- Lessons learned\n\n## Preferences\n- Communication style\n- Tools and workflows\n\nConfig Options Explained\nSetting\tPurpose\tRecommended\nenabled\tTurn on memory search\ttrue\nprovider\tEmbedding provider\t\"voyage\"\nsources\tWhat to index\t[\"memory\", \"sessions\"]\nindexMode\tWhen to index\t\"hot\" (real-time)\nminScore\tRelevance threshold\t0.3 (lower = more results)\nmaxResults\tMax snippets returned\t20\nProvider Options\nvoyage — Voyage AI embeddings (recommended)\nopenai — OpenAI embeddings\nlocal — Local embeddings (no API needed)\nSource Options\nmemory — MEMORY.md + memory/*.md files\nsessions — Past conversation transcripts\nboth — Full context (recommended)\nDaily Log Format\n\nCreate memory/logs/YYYY-MM-DD.md daily:\n\n# YYYY-MM-DD — Daily Log\n\n## [Time] — [Event/Task]\n- What happened\n- Decisions made\n- Follow-ups needed\n\n## [Time] — [Another Event]\n- Details\n\nAgent Instructions (AGENTS.md)\n\nAdd to your AGENTS.md for agent behavior:\n\n## Memory Recall\nBefore answering questions about prior work, decisions, dates, people, preferences, or todos:\n1. Run memory_search with relevant query\n2. Use memory_get to pull specific lines if needed\n3. If low confidence after search, say you checked\n\nTroubleshooting\nMemory search not working?\nCheck memorySearch.enabled: true in config\nVerify MEMORY.md exists in workspace root\nRestart gateway: clawdbot gateway restart\nResults not relevant?\nLower minScore to 0.2 for more results\nIncrease maxResults to 30\nCheck that memory files have meaningful content\nProvider errors?\nVoyage: Set VOYAGE_API_KEY in environment\nOpenAI: Set OPENAI_API_KEY in environment\nUse local provider if no API keys available\nVerification\n\nTest memory is working:\n\nUser: \"What do you remember about [past topic]?\"\nAgent: [Should search memory and return relevant context]\n\n\nIf agent has no memory, config isn't applied. Restart gateway.\n\nFull Config Example\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"voyage\",\n    \"sources\": [\"memory\", \"sessions\"],\n    \"indexMode\": \"hot\",\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  },\n  \"workspace\": \"/path/to/your/workspace\"\n}\n\nWhy This Matters\n\nWithout memory:\n\nAgent forgets everything between sessions\nRepeats questions, loses context\nNo continuity on projects\n\nWith memory:\n\nRecalls past conversations\nKnows your preferences\nTracks project history\nBuilds relationship over time\n\nGoldfish → Elephant. 🐘"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jrbobbyhansen-pixel/memory-setup",
    "publisherUrl": "https://clawhub.ai/jrbobbyhansen-pixel/memory-setup",
    "owner": "jrbobbyhansen-pixel",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/memory-setup",
    "downloadUrl": "https://openagent3.xyz/downloads/memory-setup",
    "agentUrl": "https://openagent3.xyz/skills/memory-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-setup/agent.md"
  }
}