{
  "schemaVersion": "1.0",
  "item": {
    "slug": "m2wise",
    "name": "M2Wise",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/zengyi-thinking/m2wise",
    "canonicalUrl": "https://clawhub.ai/zengyi-thinking/m2wise",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/m2wise",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=m2wise",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "EXAMPLES.md",
      "REFERENCE.md",
      "SKILL.md",
      "references/api.md",
      "references/memory.md",
      "references/wisdom.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/m2wise"
    },
    "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/m2wise",
    "agentPageUrl": "https://openagent3.xyz/skills/m2wise/agent",
    "manifestUrl": "https://openagent3.xyz/skills/m2wise/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/m2wise/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": "M2Wise - Memory-to-Wisdom Engine",
        "body": "This is a skill for the OpenClaw AI Agent to enable long-term memory and self-evolving wisdom."
      },
      {
        "title": "🎯 Purpose",
        "body": "As an AI agent, you inherently lack persistent memory across distinct sessions. The M2Wise skill bridges this gap. It allows you to:\n\nExtract and store memories (facts, preferences, commitments) from user conversations.\nRetrieve contextual memories and aggregated wisdom before answering.\nConsolidate raw memories into overarching \"Wisdom\" (rules, schemas, and skills) during idle time."
      },
      {
        "title": "🚦 When to Use This Skill",
        "body": "You should proactively invoke this skill in the following scenarios:\n\nUser expresses a preference: e.g., \"I prefer short answers\", \"Don't use emojis.\"\nUser shares a personal fact: e.g., \"I work as a Python developer\", \"I live in Beijing.\"\nUser asks you to remember: e.g., \"Remember that I hate spam.\"\nBefore answering complex questions: To recall the user's past preferences or facts to personalize your response."
      },
      {
        "title": "🛠️ How to Use (Agent Instructions)",
        "body": "You can interact with M2Wise via its Python SDK. Use your shell/execution environment to run these scripts snippet by snippet."
      },
      {
        "title": "1. Installation Requirements",
        "body": "Make sure the environment has M2Wise installed before calling its Python API:\n\npip install m2wise[all]"
      },
      {
        "title": "2. Saving Memories (Online Phase)",
        "body": "When you detect a fact or preference in the conversation, run a quick python script to save it:\n\nfrom m2wise_sdk import M2WiseSDK\n\nsdk = M2WiseSDK()\n# Extract and save the user's message\nsdk.add_message(\"current_user_id\", \"I prefer concise Chinese answers for technical questions\")"
      },
      {
        "title": "3. Retrieving Context (Online Phase)",
        "body": "Before fulfilling a user's request, fetch their relevant memories:\n\nfrom m2wise_sdk import M2WiseSDK\n\nsdk = M2WiseSDK()\ncontext = sdk.get_context(\"current_user_id\", \"How should I answer this technical question?\")\nprint(\"Retrieved Context:\", context)\n\nAction: Read the output of this script and adapt your final response to the user based on the retrieved context."
      },
      {
        "title": "4. Background Processing (Sleep & Dream)",
        "body": "It is a good practice to trigger memory consolidation periodically (e.g., at the end of a long task).\n\nfrom m2wise_sdk import M2WiseSDK\n\nsdk = M2WiseSDK()\n# Sleep: Extracts memories and groups them into Wisdom Drafts\nsdk.trigger_sleep(\"current_user_id\")\n\n# Dream: Verifies drafts against counterexamples and publishes them\nsdk.trigger_dream(\"current_user_id\")"
      },
      {
        "title": "🧩 MCP Server Alternative",
        "body": "If your OpenClaw runtime supports MCP (Model Context Protocol), you can start the M2Wise MCP server and use its native tools instead of writing Python scripts:\n\n# Start the MCP server\nm2wise-mcp --data-dir ./data\n\nAvailable MCP Tools:\n\nm2wise_add: Add memory from conversation.\nm2wise_search: Search memories and wisdom.\nm2wise_sleep: Generate wisdom drafts.\nm2wise_dream: Verify and publish wisdom."
      },
      {
        "title": "🧠 Memory and Wisdom Types You Will Encounter",
        "body": "Memories: preference (likes/dislikes), fact (states/attributes), commitment (future actions).\nWisdoms: principle (interaction guidelines), schema (behavioral patterns), skill (operational tactics)."
      },
      {
        "title": "🚀 Best Practices",
        "body": "Be Proactive: Don't wait for the user to explicitly say \"remember this\". If they state a strong preference, save it using sdk.add_message().\nContext First: For ambiguous requests, always query the memory bank first.\nConsolidate Often: Run trigger_sleep() and trigger_dream() after completing a major task to ensure your wisdom evolves and stays clean."
      },
      {
        "title": "🔗 Resources",
        "body": "GitHub Repository: https://github.com/zengyi-thinking/M2Wise.git\nInstallation via OpenClaw (ClawHub):\nnpx clawdhub@latest install m2wise"
      }
    ],
    "body": "M2Wise - Memory-to-Wisdom Engine\n\nThis is a skill for the OpenClaw AI Agent to enable long-term memory and self-evolving wisdom.\n\n🎯 Purpose\n\nAs an AI agent, you inherently lack persistent memory across distinct sessions. The M2Wise skill bridges this gap. It allows you to:\n\nExtract and store memories (facts, preferences, commitments) from user conversations.\nRetrieve contextual memories and aggregated wisdom before answering.\nConsolidate raw memories into overarching \"Wisdom\" (rules, schemas, and skills) during idle time.\n🚦 When to Use This Skill\n\nYou should proactively invoke this skill in the following scenarios:\n\nUser expresses a preference: e.g., \"I prefer short answers\", \"Don't use emojis.\"\nUser shares a personal fact: e.g., \"I work as a Python developer\", \"I live in Beijing.\"\nUser asks you to remember: e.g., \"Remember that I hate spam.\"\nBefore answering complex questions: To recall the user's past preferences or facts to personalize your response.\n🛠️ How to Use (Agent Instructions)\n\nYou can interact with M2Wise via its Python SDK. Use your shell/execution environment to run these scripts snippet by snippet.\n\n1. Installation Requirements\n\nMake sure the environment has M2Wise installed before calling its Python API:\n\npip install m2wise[all]\n\n2. Saving Memories (Online Phase)\n\nWhen you detect a fact or preference in the conversation, run a quick python script to save it:\n\nfrom m2wise_sdk import M2WiseSDK\n\nsdk = M2WiseSDK()\n# Extract and save the user's message\nsdk.add_message(\"current_user_id\", \"I prefer concise Chinese answers for technical questions\")\n\n3. Retrieving Context (Online Phase)\n\nBefore fulfilling a user's request, fetch their relevant memories:\n\nfrom m2wise_sdk import M2WiseSDK\n\nsdk = M2WiseSDK()\ncontext = sdk.get_context(\"current_user_id\", \"How should I answer this technical question?\")\nprint(\"Retrieved Context:\", context)\n\n\nAction: Read the output of this script and adapt your final response to the user based on the retrieved context.\n\n4. Background Processing (Sleep & Dream)\n\nIt is a good practice to trigger memory consolidation periodically (e.g., at the end of a long task).\n\nfrom m2wise_sdk import M2WiseSDK\n\nsdk = M2WiseSDK()\n# Sleep: Extracts memories and groups them into Wisdom Drafts\nsdk.trigger_sleep(\"current_user_id\")\n\n# Dream: Verifies drafts against counterexamples and publishes them\nsdk.trigger_dream(\"current_user_id\")\n\n🧩 MCP Server Alternative\n\nIf your OpenClaw runtime supports MCP (Model Context Protocol), you can start the M2Wise MCP server and use its native tools instead of writing Python scripts:\n\n# Start the MCP server\nm2wise-mcp --data-dir ./data\n\n\nAvailable MCP Tools:\n\nm2wise_add: Add memory from conversation.\nm2wise_search: Search memories and wisdom.\nm2wise_sleep: Generate wisdom drafts.\nm2wise_dream: Verify and publish wisdom.\n🧠 Memory and Wisdom Types You Will Encounter\nMemories: preference (likes/dislikes), fact (states/attributes), commitment (future actions).\nWisdoms: principle (interaction guidelines), schema (behavioral patterns), skill (operational tactics).\n🚀 Best Practices\nBe Proactive: Don't wait for the user to explicitly say \"remember this\". If they state a strong preference, save it using sdk.add_message().\nContext First: For ambiguous requests, always query the memory bank first.\nConsolidate Often: Run trigger_sleep() and trigger_dream() after completing a major task to ensure your wisdom evolves and stays clean.\n🔗 Resources\nGitHub Repository: https://github.com/zengyi-thinking/M2Wise.git\nInstallation via OpenClaw (ClawHub):\nnpx clawdhub@latest install m2wise"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/zengyi-thinking/m2wise",
    "publisherUrl": "https://clawhub.ai/zengyi-thinking/m2wise",
    "owner": "zengyi-thinking",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/m2wise",
    "downloadUrl": "https://openagent3.xyz/downloads/m2wise",
    "agentUrl": "https://openagent3.xyz/skills/m2wise/agent",
    "manifestUrl": "https://openagent3.xyz/skills/m2wise/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/m2wise/agent.md"
  }
}