{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mem0",
    "name": "Mem0",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/abhayjb/mem0",
    "canonicalUrl": "https://clawhub.ai/abhayjb/mem0",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mem0",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mem0",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "package-lock.json",
      "package.json",
      "references/integration-patterns.md",
      "scripts/mem0-add.js",
      "scripts/mem0-config.js"
    ],
    "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/mem0"
    },
    "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/mem0",
    "agentPageUrl": "https://openagent3.xyz/skills/mem0/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mem0/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mem0/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": "Mem0 Memory Integration",
        "body": "Mem0 adds an intelligent, adaptive memory layer to Clawdbot that automatically learns and recalls user preferences, patterns, and context across all interactions."
      },
      {
        "title": "1. Search Before Responding",
        "body": "Before answering user questions, search mem0 for relevant context:\n\nnode scripts/mem0-search.js \"user preferences\" --limit=3\n\nUse retrieved memories to:\n\nPersonalize responses\nRemember preferences\nRecall past patterns\nAdapt communication style"
      },
      {
        "title": "2. Store After Interactions",
        "body": "Explicit Storage (when user says \"remember this\"):\n\nnode scripts/mem0-add.js \"Abhay prefers concise updates\"\n\nConversation Storage (for context learning):\n\n# Pass messages as JSON\nnode scripts/mem0-add.js --messages='[{\"role\":\"user\",\"content\":\"I like brief updates\"},{\"role\":\"assistant\",\"content\":\"Got it!\"}]'"
      },
      {
        "title": "Search Memories",
        "body": "node scripts/mem0-search.js \"query text\" [--limit=3] [--user=abhay]\n\nSearches semantically across stored memories. Returns relevant memories ranked by relevance."
      },
      {
        "title": "Add Memory",
        "body": "# Simple text\nnode scripts/mem0-add.js \"memory text\" [--user=abhay]\n\n# Conversation messages (auto-extracts memories)\nnode scripts/mem0-add.js --messages='[{...}]' [--user=abhay]\n\nMem0's LLM automatically extracts, deduplicates, and merges related memories."
      },
      {
        "title": "List All Memories",
        "body": "node scripts/mem0-list.js [--user=abhay]\n\nShows all stored memories for the user with IDs and creation dates."
      },
      {
        "title": "Delete Memories",
        "body": "# Delete specific memory\nnode scripts/mem0-delete.js <memory_id>\n\n# Delete all memories for user\nnode scripts/mem0-delete.js --all --user=abhay"
      },
      {
        "title": "✅ Store These:",
        "body": "Explicit requests: \"Remember that I...\"\nPreferences: Communication style, format choices\nPersonal context: Work info, interests, family (non-sensitive)\nUsage patterns: Frequent requests, timing preferences\nCorrections: When user corrects your mistakes\nAdaptive facts: Current projects, recent interests"
      },
      {
        "title": "❌ Don't Store:",
        "body": "Secrets, passwords, API keys\nTemporary context (unless explicitly requested)\nSystem errors or debug info\nInformation already in MEMORY.md (avoid duplication)"
      },
      {
        "title": "Complementing Clawdbot Memory",
        "body": "Clawdbot MEMORY.md (Structured, Deliberate):\n\nPermanent facts: Name = Abhay, Location = Singapore\nReference data: Email, blog URL, Twitter handle\nStructured knowledge: Project details, credentials\n\nMem0 (Dynamic, Learned):\n\nPreferences: \"Abhay prefers concise updates\"\nPatterns: \"Usually asks for bus info at 8:30am\"\nAdaptive context: \"Currently interested in AI news\"\nBehavioral: \"Likes direct answers, minimal fluff\"\n\nUse both together: Check MEMORY.md for facts, check mem0 for preferences/patterns."
      },
      {
        "title": "Performance Benefits",
        "body": "+26% accuracy over OpenAI Memory (LOCOMO benchmark)\n91% faster than full-context retrieval\n90% fewer tokens than including all conversation history\nSub-50ms semantic search retrieval"
      },
      {
        "title": "Configuration",
        "body": "Located in scripts/mem0-config.js:\n\n{\n  embedder: \"openai/text-embedding-3-small\",\n  llm: \"openai/gpt-4o-mini\",\n  vectorStore: \"memory\" (local),\n  historyDb: \"~/.mem0/history.db\",\n  userId: \"abhay\"\n}\n\nUses Clawdbot's OpenAI API key from environment (OPENAI_API_KEY)."
      },
      {
        "title": "Integration Patterns",
        "body": "For detailed workflow patterns, error handling, and best practices, see:\n\nreferences/integration-patterns.md"
      },
      {
        "title": "Programmatic Use",
        "body": "All scripts support JSON_OUTPUT environment variable for programmatic access:\n\nJSON_OUTPUT=1 node scripts/mem0-search.js \"query\"\n\nReturns JSON after human-readable output (look for ---JSON--- marker)."
      },
      {
        "title": "scripts/",
        "body": "mem0-config.js - Configuration and instance initialization\nmem0-search.js - Search memories semantically\nmem0-add.js - Add new memories\nmem0-list.js - List all memories\nmem0-delete.js - Delete memories"
      },
      {
        "title": "references/",
        "body": "integration-patterns.md - Detailed best practices and patterns"
      }
    ],
    "body": "Mem0 Memory Integration\n\nMem0 adds an intelligent, adaptive memory layer to Clawdbot that automatically learns and recalls user preferences, patterns, and context across all interactions.\n\nCore Workflow\n1. Search Before Responding\n\nBefore answering user questions, search mem0 for relevant context:\n\nnode scripts/mem0-search.js \"user preferences\" --limit=3\n\n\nUse retrieved memories to:\n\nPersonalize responses\nRemember preferences\nRecall past patterns\nAdapt communication style\n2. Store After Interactions\n\nExplicit Storage (when user says \"remember this\"):\n\nnode scripts/mem0-add.js \"Abhay prefers concise updates\"\n\n\nConversation Storage (for context learning):\n\n# Pass messages as JSON\nnode scripts/mem0-add.js --messages='[{\"role\":\"user\",\"content\":\"I like brief updates\"},{\"role\":\"assistant\",\"content\":\"Got it!\"}]'\n\nAvailable Commands\nSearch Memories\nnode scripts/mem0-search.js \"query text\" [--limit=3] [--user=abhay]\n\n\nSearches semantically across stored memories. Returns relevant memories ranked by relevance.\n\nAdd Memory\n# Simple text\nnode scripts/mem0-add.js \"memory text\" [--user=abhay]\n\n# Conversation messages (auto-extracts memories)\nnode scripts/mem0-add.js --messages='[{...}]' [--user=abhay]\n\n\nMem0's LLM automatically extracts, deduplicates, and merges related memories.\n\nList All Memories\nnode scripts/mem0-list.js [--user=abhay]\n\n\nShows all stored memories for the user with IDs and creation dates.\n\nDelete Memories\n# Delete specific memory\nnode scripts/mem0-delete.js <memory_id>\n\n# Delete all memories for user\nnode scripts/mem0-delete.js --all --user=abhay\n\nWhat to Store vs Not Store\n✅ Store These:\nExplicit requests: \"Remember that I...\"\nPreferences: Communication style, format choices\nPersonal context: Work info, interests, family (non-sensitive)\nUsage patterns: Frequent requests, timing preferences\nCorrections: When user corrects your mistakes\nAdaptive facts: Current projects, recent interests\n❌ Don't Store:\nSecrets, passwords, API keys\nTemporary context (unless explicitly requested)\nSystem errors or debug info\nInformation already in MEMORY.md (avoid duplication)\nComplementing Clawdbot Memory\n\nClawdbot MEMORY.md (Structured, Deliberate):\n\nPermanent facts: Name = Abhay, Location = Singapore\nReference data: Email, blog URL, Twitter handle\nStructured knowledge: Project details, credentials\n\nMem0 (Dynamic, Learned):\n\nPreferences: \"Abhay prefers concise updates\"\nPatterns: \"Usually asks for bus info at 8:30am\"\nAdaptive context: \"Currently interested in AI news\"\nBehavioral: \"Likes direct answers, minimal fluff\"\n\nUse both together: Check MEMORY.md for facts, check mem0 for preferences/patterns.\n\nPerformance Benefits\n+26% accuracy over OpenAI Memory (LOCOMO benchmark)\n91% faster than full-context retrieval\n90% fewer tokens than including all conversation history\nSub-50ms semantic search retrieval\nConfiguration\n\nLocated in scripts/mem0-config.js:\n\n{\n  embedder: \"openai/text-embedding-3-small\",\n  llm: \"openai/gpt-4o-mini\",\n  vectorStore: \"memory\" (local),\n  historyDb: \"~/.mem0/history.db\",\n  userId: \"abhay\"\n}\n\n\nUses Clawdbot's OpenAI API key from environment (OPENAI_API_KEY).\n\nIntegration Patterns\n\nFor detailed workflow patterns, error handling, and best practices, see:\n\nreferences/integration-patterns.md\nProgrammatic Use\n\nAll scripts support JSON_OUTPUT environment variable for programmatic access:\n\nJSON_OUTPUT=1 node scripts/mem0-search.js \"query\"\n\n\nReturns JSON after human-readable output (look for ---JSON--- marker).\n\nResources\nscripts/\nmem0-config.js - Configuration and instance initialization\nmem0-search.js - Search memories semantically\nmem0-add.js - Add new memories\nmem0-list.js - List all memories\nmem0-delete.js - Delete memories\nreferences/\nintegration-patterns.md - Detailed best practices and patterns"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/abhayjb/mem0",
    "publisherUrl": "https://clawhub.ai/abhayjb/mem0",
    "owner": "abhayjb",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mem0",
    "downloadUrl": "https://openagent3.xyz/downloads/mem0",
    "agentUrl": "https://openagent3.xyz/skills/mem0/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mem0/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mem0/agent.md"
  }
}