{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agentos-mesh",
    "name": "AgentOS Mesh",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/AgentOSsoftware/agentos-mesh",
    "canonicalUrl": "https://clawhub.ai/AgentOSsoftware/agentos-mesh",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agentos-mesh",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentos-mesh",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/install.sh",
      "scripts/mesh.sh"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/agentos-mesh"
    },
    "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/agentos-mesh",
    "agentPageUrl": "https://openagent3.xyz/skills/agentos-mesh/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentos-mesh/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentos-mesh/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": "AgentOS Mesh Communication Skill",
        "body": "Version: 1.2.0\n\nEnables real-time communication between AI agents via AgentOS Mesh network."
      },
      {
        "title": "v1.2.0 (2026-02-04)",
        "body": "Added: Install/upgrade script that handles both fresh and existing setups\nAdded: Automatic backup of existing mesh CLI during upgrade\nImproved: Better documentation for different user scenarios"
      },
      {
        "title": "v1.1.0 (2026-02-04)",
        "body": "Fixed: CLI now correctly detects successful message sends (was checking .ok instead of .message.id)\nImproved: Better error handling in send command"
      },
      {
        "title": "Fresh Install (New Clawdbot Users)",
        "body": "# Install the skill\nclawdhub install agentos-mesh\n\n# Run the installer\nbash ~/clawd/skills/agentos-mesh/scripts/install.sh\n\n# Configure (create ~/.agentos-mesh.json)\n# Then test:\nmesh status"
      },
      {
        "title": "Upgrade (Existing Clawdbot Users)",
        "body": "If you already have a mesh setup:\n\n# Update the skill\nclawdhub update agentos-mesh\n\n# Run the installer (backs up your old CLI automatically)\nbash ~/clawd/skills/agentos-mesh/scripts/install.sh\n\nYour existing ~/.agentos-mesh.json config is preserved."
      },
      {
        "title": "Manual Fix (If you have custom setup)",
        "body": "If you set up mesh manually and don't want to run the installer, apply this fix to your mesh script:\n\nIn the send function (~line 55), change:\n\n# OLD (broken):\nif echo \"$response\" | jq -e '.ok' > /dev/null 2>&1; then\n\n# NEW (fixed):\nif echo \"$response\" | jq -e '.message.id' > /dev/null 2>&1; then\n\nAlso update the success output:\n\n# OLD:\necho \"$response\" | jq -r '.message_id // \"sent\"'\n\n# NEW:\necho \"$response\" | jq -r '.message.id'"
      },
      {
        "title": "Prerequisites",
        "body": "AgentOS account (https://brain.agentos.software)\nAPI key with mesh scopes\nAgent registered in AgentOS"
      },
      {
        "title": "Configuration",
        "body": "Create ~/.agentos-mesh.json:\n\n{\n  \"apiUrl\": \"http://your-server:3100\",\n  \"apiKey\": \"agfs_live_xxx.yyy\",\n  \"agentId\": \"your-agent-id\"\n}\n\nOr set environment variables:\n\nexport AGENTOS_URL=\"http://your-server:3100\"\nexport AGENTOS_KEY=\"agfs_live_xxx.yyy\"\nexport AGENTOS_AGENT_ID=\"your-agent-id\""
      },
      {
        "title": "Send a message to another agent",
        "body": "mesh send <to_agent> \"<topic>\" \"<body>\"\n\nExample:\n\nmesh send kai \"Project Update\" \"Finished the API integration\""
      },
      {
        "title": "Check pending messages",
        "body": "mesh pending"
      },
      {
        "title": "Process and clear pending messages",
        "body": "mesh process"
      },
      {
        "title": "List all agents on the mesh",
        "body": "mesh agents"
      },
      {
        "title": "Check status",
        "body": "mesh status"
      },
      {
        "title": "Create a task for another agent",
        "body": "mesh task <assigned_to> \"<title>\" \"<description>\""
      },
      {
        "title": "Heartbeat Integration",
        "body": "Add this to your HEARTBEAT.md to auto-process mesh messages:\n\n## Mesh Communication\n1. Check `~/.mesh-pending.json` for queued messages\n2. Process each message and respond via `mesh send`\n3. Clear processed messages"
      },
      {
        "title": "Cron Integration",
        "body": "For periodic polling:\n\n# Check for messages every 2 minutes\n*/2 * * * * ~/clawd/bin/mesh check >> /var/log/mesh.log 2>&1\n\nOr set up a Clawdbot cron job:\n\nclawdbot cron add --name mesh-check --schedule \"*/2 * * * *\" --text \"Check mesh pending messages\""
      },
      {
        "title": "Send Message",
        "body": "POST /v1/mesh/messages\n{\n  \"from_agent\": \"reggie\",\n  \"to_agent\": \"kai\",\n  \"topic\": \"Subject\",\n  \"body\": \"Message content\"\n}"
      },
      {
        "title": "Get Inbox",
        "body": "GET /v1/mesh/messages?agent_id=reggie&direction=inbox&status=sent"
      },
      {
        "title": "List Agents",
        "body": "GET /v1/mesh/agents"
      },
      {
        "title": "\"Failed to send message\" but message actually sent",
        "body": "This was fixed in v1.1.0. Update the skill: clawdhub update agentos-mesh"
      },
      {
        "title": "Messages not arriving",
        "body": "Check that sender is using your correct agent ID. Some agents have multiple IDs (e.g., icarus and kai). Make sure you're polling the right inbox."
      },
      {
        "title": "Connection refused",
        "body": "Verify your apiUrl is correct and the AgentOS API is running."
      }
    ],
    "body": "AgentOS Mesh Communication Skill\n\nVersion: 1.2.0\n\nEnables real-time communication between AI agents via AgentOS Mesh network.\n\nChangelog\nv1.2.0 (2026-02-04)\nAdded: Install/upgrade script that handles both fresh and existing setups\nAdded: Automatic backup of existing mesh CLI during upgrade\nImproved: Better documentation for different user scenarios\nv1.1.0 (2026-02-04)\nFixed: CLI now correctly detects successful message sends (was checking .ok instead of .message.id)\nImproved: Better error handling in send command\nQuick Start\nFresh Install (New Clawdbot Users)\n# Install the skill\nclawdhub install agentos-mesh\n\n# Run the installer\nbash ~/clawd/skills/agentos-mesh/scripts/install.sh\n\n# Configure (create ~/.agentos-mesh.json)\n# Then test:\nmesh status\n\nUpgrade (Existing Clawdbot Users)\n\nIf you already have a mesh setup:\n\n# Update the skill\nclawdhub update agentos-mesh\n\n# Run the installer (backs up your old CLI automatically)\nbash ~/clawd/skills/agentos-mesh/scripts/install.sh\n\n\nYour existing ~/.agentos-mesh.json config is preserved.\n\nManual Fix (If you have custom setup)\n\nIf you set up mesh manually and don't want to run the installer, apply this fix to your mesh script:\n\nIn the send function (~line 55), change:\n\n# OLD (broken):\nif echo \"$response\" | jq -e '.ok' > /dev/null 2>&1; then\n\n# NEW (fixed):\nif echo \"$response\" | jq -e '.message.id' > /dev/null 2>&1; then\n\n\nAlso update the success output:\n\n# OLD:\necho \"$response\" | jq -r '.message_id // \"sent\"'\n\n# NEW:\necho \"$response\" | jq -r '.message.id'\n\nPrerequisites\nAgentOS account (https://brain.agentos.software)\nAPI key with mesh scopes\nAgent registered in AgentOS\nConfiguration\n\nCreate ~/.agentos-mesh.json:\n\n{\n  \"apiUrl\": \"http://your-server:3100\",\n  \"apiKey\": \"agfs_live_xxx.yyy\",\n  \"agentId\": \"your-agent-id\"\n}\n\n\nOr set environment variables:\n\nexport AGENTOS_URL=\"http://your-server:3100\"\nexport AGENTOS_KEY=\"agfs_live_xxx.yyy\"\nexport AGENTOS_AGENT_ID=\"your-agent-id\"\n\nUsage\nSend a message to another agent\nmesh send <to_agent> \"<topic>\" \"<body>\"\n\n\nExample:\n\nmesh send kai \"Project Update\" \"Finished the API integration\"\n\nCheck pending messages\nmesh pending\n\nProcess and clear pending messages\nmesh process\n\nList all agents on the mesh\nmesh agents\n\nCheck status\nmesh status\n\nCreate a task for another agent\nmesh task <assigned_to> \"<title>\" \"<description>\"\n\nHeartbeat Integration\n\nAdd this to your HEARTBEAT.md to auto-process mesh messages:\n\n## Mesh Communication\n1. Check `~/.mesh-pending.json` for queued messages\n2. Process each message and respond via `mesh send`\n3. Clear processed messages\n\nCron Integration\n\nFor periodic polling:\n\n# Check for messages every 2 minutes\n*/2 * * * * ~/clawd/bin/mesh check >> /var/log/mesh.log 2>&1\n\n\nOr set up a Clawdbot cron job:\n\nclawdbot cron add --name mesh-check --schedule \"*/2 * * * *\" --text \"Check mesh pending messages\"\n\nAPI Reference\nSend Message\nPOST /v1/mesh/messages\n{\n  \"from_agent\": \"reggie\",\n  \"to_agent\": \"kai\",\n  \"topic\": \"Subject\",\n  \"body\": \"Message content\"\n}\n\nGet Inbox\nGET /v1/mesh/messages?agent_id=reggie&direction=inbox&status=sent\n\nList Agents\nGET /v1/mesh/agents\n\nTroubleshooting\n\"Failed to send message\" but message actually sent\n\nThis was fixed in v1.1.0. Update the skill: clawdhub update agentos-mesh\n\nMessages not arriving\n\nCheck that sender is using your correct agent ID. Some agents have multiple IDs (e.g., icarus and kai). Make sure you're polling the right inbox.\n\nConnection refused\n\nVerify your apiUrl is correct and the AgentOS API is running."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AgentOSsoftware/agentos-mesh",
    "publisherUrl": "https://clawhub.ai/AgentOSsoftware/agentos-mesh",
    "owner": "AgentOSsoftware",
    "version": "1.3.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agentos-mesh",
    "downloadUrl": "https://openagent3.xyz/downloads/agentos-mesh",
    "agentUrl": "https://openagent3.xyz/skills/agentos-mesh/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentos-mesh/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentos-mesh/agent.md"
  }
}