{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clude-memory-mcp",
    "name": "Clude Memory MCP",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/sebbsssss/clude-memory-mcp",
    "canonicalUrl": "https://clawhub.ai/sebbsssss/clude-memory-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clude-memory-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clude-memory-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "server.ts",
      "supabase-schema.sql"
    ],
    "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/clude-memory-mcp"
    },
    "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/clude-memory-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/clude-memory-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clude-memory-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clude-memory-mcp/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": "Clude Memory MCP",
        "body": "MCP server exposing a 4-tier cognitive memory architecture inspired by Stanford's Generative Agents (Park et al. 2023)."
      },
      {
        "title": "recall_memories",
        "body": "Search the memory system. Returns scored memories ranked by relevance, importance, recency, and vector similarity.\n\nquery — text to search against memory summaries\ntags — filter by tags\nrelated_user — filter by user/agent ID\nmemory_types — filter by type: episodic, semantic, procedural, self_model\nlimit — max results (1-20, default 5)\nmin_importance — minimum importance threshold (0-1)"
      },
      {
        "title": "store_memory",
        "body": "Store a new memory. Memories persist across conversations, decay over time if not accessed, and get committed to Solana.\n\ntype — episodic (events), semantic (knowledge), procedural (behaviors), self_model (identity)\ncontent — full memory content\nsummary — short summary for recall matching\ntags — tags for filtering\nimportance — importance score 0-1\nsource — origin identifier (e.g. mcp:my-agent)"
      },
      {
        "title": "get_memory_stats",
        "body": "Get statistics: counts by type, average importance/decay, dream session history, top tags."
      },
      {
        "title": "get_market_mood",
        "body": "Get current market mood and price state (no LLM call)."
      },
      {
        "title": "ask_clude",
        "body": "Ask Clude a question and get an in-character response. Calls Claude API."
      },
      {
        "title": "Setup",
        "body": "npm install clude-bot\n\nRequires a Supabase project with the schema from supabase-schema.sql. Set SUPABASE_URL and SUPABASE_SERVICE_KEY environment variables."
      },
      {
        "title": "Architecture",
        "body": "4-tier memory: episodic (7%/day decay), semantic (2%/day), procedural (3%/day), self_model (1%/day)\nHybrid retrieval: pgvector cosine similarity + keyword matching + tag scoring\nDream cycles: consolidation, reflection, emergence — every 6 hours\nOn-chain commitment: SHA-256 hashed memories committed to Solana via memo transactions\nGranular decomposition: per-fragment embeddings for precise sub-memory retrieval"
      },
      {
        "title": "License",
        "body": "MIT"
      }
    ],
    "body": "Clude Memory MCP\n\nMCP server exposing a 4-tier cognitive memory architecture inspired by Stanford's Generative Agents (Park et al. 2023).\n\nTools\nrecall_memories\n\nSearch the memory system. Returns scored memories ranked by relevance, importance, recency, and vector similarity.\n\nquery — text to search against memory summaries\ntags — filter by tags\nrelated_user — filter by user/agent ID\nmemory_types — filter by type: episodic, semantic, procedural, self_model\nlimit — max results (1-20, default 5)\nmin_importance — minimum importance threshold (0-1)\nstore_memory\n\nStore a new memory. Memories persist across conversations, decay over time if not accessed, and get committed to Solana.\n\ntype — episodic (events), semantic (knowledge), procedural (behaviors), self_model (identity)\ncontent — full memory content\nsummary — short summary for recall matching\ntags — tags for filtering\nimportance — importance score 0-1\nsource — origin identifier (e.g. mcp:my-agent)\nget_memory_stats\n\nGet statistics: counts by type, average importance/decay, dream session history, top tags.\n\nget_market_mood\n\nGet current market mood and price state (no LLM call).\n\nask_clude\n\nAsk Clude a question and get an in-character response. Calls Claude API.\n\nSetup\nnpm install clude-bot\n\n\nRequires a Supabase project with the schema from supabase-schema.sql. Set SUPABASE_URL and SUPABASE_SERVICE_KEY environment variables.\n\nArchitecture\n4-tier memory: episodic (7%/day decay), semantic (2%/day), procedural (3%/day), self_model (1%/day)\nHybrid retrieval: pgvector cosine similarity + keyword matching + tag scoring\nDream cycles: consolidation, reflection, emergence — every 6 hours\nOn-chain commitment: SHA-256 hashed memories committed to Solana via memo transactions\nGranular decomposition: per-fragment embeddings for precise sub-memory retrieval\nLicense\n\nMIT"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/sebbsssss/clude-memory-mcp",
    "publisherUrl": "https://clawhub.ai/sebbsssss/clude-memory-mcp",
    "owner": "sebbsssss",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clude-memory-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/clude-memory-mcp",
    "agentUrl": "https://openagent3.xyz/skills/clude-memory-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clude-memory-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clude-memory-mcp/agent.md"
  }
}