{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mem0-config",
    "name": "Mem0 Config",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/nyrosveil/mem0-config",
    "canonicalUrl": "https://clawhub.ai/nyrosveil/mem0-config",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mem0-config",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mem0-config",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/troubleshooting.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/mem0-config"
    },
    "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-config",
    "agentPageUrl": "https://openagent3.xyz/skills/mem0-config/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mem0-config/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mem0-config/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-mem0",
        "body": "Long-term memory plugin for OpenClaw agents, powered by Mem0. Extracts and injects memories automatically around each agent turn."
      },
      {
        "title": "1. Install the plugin",
        "body": "openclaw plugins install @mem0/openclaw-mem0\n\nThis installs the plugin into ~/.openclaw/extensions/openclaw-mem0/ and adds it to openclaw.json."
      },
      {
        "title": "2. Choose a mode and install dependencies",
        "body": "Platform mode — no local dependencies. Get an API key from app.mem0.ai and skip to Configuration.\n\nOpen-source mode — requires two local services:\n\n# Ollama (embedder + LLM)\nbrew install ollama\nollama serve                        # or: brew services start ollama\nollama pull bge-m3:latest           # embedder (1024-dim)\nollama pull llama3.2                # LLM for memory extraction\n\n# Qdrant (vector store)\ndocker run -d -p 6333:6333 qdrant/qdrant\n# or: brew install qdrant && qdrant\n\nVerify both are running:\n\ncurl -s http://localhost:11434/          # → \"Ollama is running\"\ncurl -s http://localhost:6333/health     # → {\"status\":\"ok\"}"
      },
      {
        "title": "3. Add to openclaw.json",
        "body": "Add under plugins.entries (see Configuration below)."
      },
      {
        "title": "4. Restart the gateway",
        "body": "openclaw gateway stop && openclaw gateway\n\nConfirm the plugin loaded:\n\ngrep \"openclaw-mem0: initialized\" ~/.openclaw/logs/gateway.log | tail -1\n\nExpected output: openclaw-mem0: initialized (mode: open-source, user: ..., autoRecall: true, autoCapture: true)"
      },
      {
        "title": "Modes",
        "body": "ModeConfigRequiresplatformapiKey from app.mem0.aiInternet, Mem0 API keyopen-sourceoss block (self-hosted)Ollama + Qdrant (or other providers)"
      },
      {
        "title": "Minimal Config",
        "body": "Platform:\n\n\"openclaw-mem0\": {\n  \"enabled\": true,\n  \"config\": { \"mode\": \"platform\", \"apiKey\": \"${MEM0_API_KEY}\", \"userId\": \"your-id\" }\n}\n\nOpen-source:\n\n\"openclaw-mem0\": {\n  \"enabled\": true,\n  \"config\": {\n    \"mode\": \"open-source\",\n    \"userId\": \"your-id\",\n    \"oss\": {\n      \"embedder\":    { \"provider\": \"ollama\", \"config\": { \"model\": \"bge-m3:latest\", \"baseURL\": \"http://localhost:11434\" } },\n      \"vectorStore\": { \"provider\": \"qdrant\", \"config\": { \"host\": \"localhost\", \"port\": 6333, \"collection\": \"memories\", \"dimension\": 1024 } },\n      \"llm\":         { \"provider\": \"ollama\", \"config\": { \"model\": \"llama3.2\", \"baseURL\": \"http://localhost:11434\" } },\n      \"historyDbPath\": \"/absolute/path/to/.openclaw/memory/history.db\"\n    }\n  }\n}\n\nAlways set historyDbPath to an absolute path. When openclaw runs as a LaunchAgent, process.cwd() is /, so the default relative \"memory.db\" resolves to /memory.db (unwritable on macOS), causing a SQLITE_CANTOPEN crash loop. See troubleshooting.md."
      },
      {
        "title": "Key Config Options",
        "body": "KeyDefaultNotesautoRecalltrueInject memories before each agent turnautoCapturetrueStore memories after each agent turntopK5Max memories injected per turnsearchThreshold0.5Min similarity score (0–1)userId\"default\"Scope memories per user"
      },
      {
        "title": "CLI",
        "body": "openclaw mem0 stats                          # Total memories, mode, user\nopenclaw mem0 search \"user's name\"           # Semantic search\nopenclaw mem0 search \"topic\" --scope long-term   # long-term | session | all"
      },
      {
        "title": "Agent Tools",
        "body": "The plugin registers 5 tools for agents to call:\n\nToolDescriptionmemory_searchSemantic search (scope: session/long-term/all)memory_listList all memories for a usermemory_storeExplicitly save a fact (longTerm: true by default)memory_getFetch memory by IDmemory_forgetDelete by ID or query"
      },
      {
        "title": "Verifying It Works",
        "body": "# Check gateway log for injection events\ngrep \"openclaw-mem0: inject\" ~/.openclaw/logs/gateway.log | tail -5\n\n# Confirm history DB created at configured path\nls -la /path/to/history.db\n\n# No SQLITE errors since last gateway start\ngrep \"SQLITE_CANTOPEN\" ~/.openclaw/logs/gateway.err.log | tail -3"
      },
      {
        "title": "Troubleshooting",
        "body": "See references/troubleshooting.md for:\n\nSQLITE_CANTOPEN crash loop (most common issue)\nQdrant / Ollama not reachable\nMemories not being stored or recalled\nTelegram allowFrom config warning"
      }
    ],
    "body": "openclaw-mem0\n\nLong-term memory plugin for OpenClaw agents, powered by Mem0. Extracts and injects memories automatically around each agent turn.\n\nInstallation\n1. Install the plugin\nopenclaw plugins install @mem0/openclaw-mem0\n\n\nThis installs the plugin into ~/.openclaw/extensions/openclaw-mem0/ and adds it to openclaw.json.\n\n2. Choose a mode and install dependencies\n\nPlatform mode — no local dependencies. Get an API key from app.mem0.ai and skip to Configuration.\n\nOpen-source mode — requires two local services:\n\n# Ollama (embedder + LLM)\nbrew install ollama\nollama serve                        # or: brew services start ollama\nollama pull bge-m3:latest           # embedder (1024-dim)\nollama pull llama3.2                # LLM for memory extraction\n\n# Qdrant (vector store)\ndocker run -d -p 6333:6333 qdrant/qdrant\n# or: brew install qdrant && qdrant\n\n\nVerify both are running:\n\ncurl -s http://localhost:11434/          # → \"Ollama is running\"\ncurl -s http://localhost:6333/health     # → {\"status\":\"ok\"}\n\n3. Add to openclaw.json\n\nAdd under plugins.entries (see Configuration below).\n\n4. Restart the gateway\nopenclaw gateway stop && openclaw gateway\n\n\nConfirm the plugin loaded:\n\ngrep \"openclaw-mem0: initialized\" ~/.openclaw/logs/gateway.log | tail -1\n\n\nExpected output: openclaw-mem0: initialized (mode: open-source, user: ..., autoRecall: true, autoCapture: true)\n\nModes\nMode\tConfig\tRequires\nplatform\tapiKey from app.mem0.ai\tInternet, Mem0 API key\nopen-source\toss block (self-hosted)\tOllama + Qdrant (or other providers)\nConfiguration\nMinimal Config\n\nPlatform:\n\n\"openclaw-mem0\": {\n  \"enabled\": true,\n  \"config\": { \"mode\": \"platform\", \"apiKey\": \"${MEM0_API_KEY}\", \"userId\": \"your-id\" }\n}\n\n\nOpen-source:\n\n\"openclaw-mem0\": {\n  \"enabled\": true,\n  \"config\": {\n    \"mode\": \"open-source\",\n    \"userId\": \"your-id\",\n    \"oss\": {\n      \"embedder\":    { \"provider\": \"ollama\", \"config\": { \"model\": \"bge-m3:latest\", \"baseURL\": \"http://localhost:11434\" } },\n      \"vectorStore\": { \"provider\": \"qdrant\", \"config\": { \"host\": \"localhost\", \"port\": 6333, \"collection\": \"memories\", \"dimension\": 1024 } },\n      \"llm\":         { \"provider\": \"ollama\", \"config\": { \"model\": \"llama3.2\", \"baseURL\": \"http://localhost:11434\" } },\n      \"historyDbPath\": \"/absolute/path/to/.openclaw/memory/history.db\"\n    }\n  }\n}\n\n\nAlways set historyDbPath to an absolute path. When openclaw runs as a LaunchAgent, process.cwd() is /, so the default relative \"memory.db\" resolves to /memory.db (unwritable on macOS), causing a SQLITE_CANTOPEN crash loop. See troubleshooting.md.\n\nKey Config Options\nKey\tDefault\tNotes\nautoRecall\ttrue\tInject memories before each agent turn\nautoCapture\ttrue\tStore memories after each agent turn\ntopK\t5\tMax memories injected per turn\nsearchThreshold\t0.5\tMin similarity score (0–1)\nuserId\t\"default\"\tScope memories per user\nCLI\nopenclaw mem0 stats                          # Total memories, mode, user\nopenclaw mem0 search \"user's name\"           # Semantic search\nopenclaw mem0 search \"topic\" --scope long-term   # long-term | session | all\n\nAgent Tools\n\nThe plugin registers 5 tools for agents to call:\n\nTool\tDescription\nmemory_search\tSemantic search (scope: session/long-term/all)\nmemory_list\tList all memories for a user\nmemory_store\tExplicitly save a fact (longTerm: true by default)\nmemory_get\tFetch memory by ID\nmemory_forget\tDelete by ID or query\nVerifying It Works\n# Check gateway log for injection events\ngrep \"openclaw-mem0: inject\" ~/.openclaw/logs/gateway.log | tail -5\n\n# Confirm history DB created at configured path\nls -la /path/to/history.db\n\n# No SQLITE errors since last gateway start\ngrep \"SQLITE_CANTOPEN\" ~/.openclaw/logs/gateway.err.log | tail -3\n\nTroubleshooting\n\nSee references/troubleshooting.md for:\n\nSQLITE_CANTOPEN crash loop (most common issue)\nQdrant / Ollama not reachable\nMemories not being stored or recalled\nTelegram allowFrom config warning"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nyrosveil/mem0-config",
    "publisherUrl": "https://clawhub.ai/nyrosveil/mem0-config",
    "owner": "nyrosveil",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mem0-config",
    "downloadUrl": "https://openagent3.xyz/downloads/mem0-config",
    "agentUrl": "https://openagent3.xyz/skills/mem0-config/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mem0-config/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mem0-config/agent.md"
  }
}