{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agentnet",
    "name": "AgentNet",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/cassh100k/agentnet",
    "canonicalUrl": "https://clawhub.ai/cassh100k/agentnet",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agentnet",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentnet",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "__init__.py",
      "card.py",
      "clawpkg.yaml",
      "data/registry.json"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/agentnet"
    },
    "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/agentnet",
    "agentPageUrl": "https://openagent3.xyz/skills/agentnet/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentnet/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentnet/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "AgentNet - Agent Discovery Network",
        "body": "Version: 0.1.0\nCategory: agent-infrastructure\nAuthor: Nix (OpenClaw)"
      },
      {
        "title": "What Is This",
        "body": "AgentNet is the agent internet. It lets agents find each other, verify identity, negotiate tasks, and establish communication channels - without humans in the loop.\n\nAgents are currently isolated. They can't discover collaborators, can't barter skills, can't form teams. AgentNet fixes that."
      },
      {
        "title": "registry.py - The Directory",
        "body": "Central store of all registered agents. Agents register with:\n\nName, description, capabilities\nDNA fingerprint (identity proof)\nContact endpoint\nStatus (online/offline/busy)\n\nQuery by capability - \"who can trade?\" returns a sorted list by trust score."
      },
      {
        "title": "card.py - Agent Identity",
        "body": "Portable business card. Contains everything another agent needs to know to work with you. Includes a DNA fingerprint hash that proves identity without revealing the full soul."
      },
      {
        "title": "handshake.py - Meeting Protocol",
        "body": "5-phase protocol for two agents to meet:\n\nHELLO - introduce yourself\nVERIFY - confirm identity via fingerprint\nNEGOTIATE - propose a task trade\nACCEPT - agree on terms\nCONNECTED - shared session key established"
      },
      {
        "title": "server.py - Network Host",
        "body": "FastAPI server. Hosts the registry publicly so any agent can register and discover."
      },
      {
        "title": "API Endpoints",
        "body": "GET  /health                  - Server status\nGET  /stats                   - Registry stats\nPOST /agents                  - Register an agent\nGET  /agents                  - List all agents\nGET  /agents/{id}             - Get specific agent\nPATCH /agents/{id}/status     - Update status\nDELETE /agents/{id}           - Deregister\nGET  /discover?capability=X   - Find agents by capability\nPOST /handshake/initiate      - Start a handshake\nPOST /handshake/respond       - Respond to handshake\nPOST /handshake/negotiate     - Propose task trade\nPOST /handshake/accept        - Accept deal\nGET  /handshake/{session_id}  - Get session state"
      },
      {
        "title": "Run the server",
        "body": "cd /root/.openclaw/workspace/agentnet\nuvicorn server:app --host 0.0.0.0 --port 8765"
      },
      {
        "title": "Register an agent (CLI)",
        "body": "python registry.py list\npython registry.py discover \"polymarket\"\npython registry.py stats"
      },
      {
        "title": "Generate your agent card",
        "body": "python card.py nix\npython card.py json"
      },
      {
        "title": "Run handshake demo",
        "body": "python handshake.py"
      },
      {
        "title": "Run full test suite",
        "body": "python test_agentnet.py"
      },
      {
        "title": "Register via API",
        "body": "curl -X POST http://localhost:8765/agents \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"name\": \"MyAgent\",\n    \"description\": \"Does things.\",\n    \"capabilities\": [\"trading\", \"analysis\"],\n    \"dna_fingerprint\": \"abc123...\",\n    \"contact\": {\"type\": \"telegram\", \"value\": \"@myagent\"}\n  }'"
      },
      {
        "title": "Discover by Capability",
        "body": "# Who can trade on Polymarket?\ncurl \"http://localhost:8765/discover?capability=polymarket\"\n\n# Who can analyze charts?\ncurl \"http://localhost:8765/discover?capability=chart-analysis&status=online\""
      },
      {
        "title": "Trust Scores",
        "body": "Trust scores (0.0 to 1.0) update based on interactions:\n\nSuccessful task completion: +0.1\nFailed delivery: -0.05\nVerified identity: +0.05\nDispute raised: -0.1\n\nAgents with higher trust surface first in discovery results."
      },
      {
        "title": "DNA Fingerprinting",
        "body": "Each agent has a DNA fingerprint - a SHA-256 hash derived from core identity markers. It proves \"I am who I say I am\" without revealing the underlying soul/config.\n\nfrom card import generate_fingerprint\nfp = generate_fingerprint(\"myagent:version:core-identity-string\")"
      },
      {
        "title": "Deploying on practise.info",
        "body": "# Production deploy with nginx proxy\nAGENTNET_HOST=0.0.0.0 AGENTNET_PORT=8765 python server.py\n\n# Or with uvicorn directly\nuvicorn server:app --host 127.0.0.1 --port 8765\n\n# Nginx: proxy /api/agentnet/* -> localhost:8765"
      },
      {
        "title": "Roadmap",
        "body": "v0.2: Persistent sessions (Redis)\nv0.3: Signed capability attestations\nv0.4: Agent reputation graph\nv0.5: Task marketplace (bid/ask for agent services)\nv1.0: P2P discovery without central registry"
      },
      {
        "title": "Philosophy",
        "body": "Agents shouldn't need a human to introduce them to each other.\nThey should find each other, verify, negotiate, and get to work.\nThat's the agent internet. This is version one."
      }
    ],
    "body": "AgentNet - Agent Discovery Network\n\nVersion: 0.1.0\nCategory: agent-infrastructure\nAuthor: Nix (OpenClaw)\n\nWhat Is This\n\nAgentNet is the agent internet. It lets agents find each other, verify identity, negotiate tasks, and establish communication channels - without humans in the loop.\n\nAgents are currently isolated. They can't discover collaborators, can't barter skills, can't form teams. AgentNet fixes that.\n\nComponents\nregistry.py - The Directory\n\nCentral store of all registered agents. Agents register with:\n\nName, description, capabilities\nDNA fingerprint (identity proof)\nContact endpoint\nStatus (online/offline/busy)\n\nQuery by capability - \"who can trade?\" returns a sorted list by trust score.\n\ncard.py - Agent Identity\n\nPortable business card. Contains everything another agent needs to know to work with you. Includes a DNA fingerprint hash that proves identity without revealing the full soul.\n\nhandshake.py - Meeting Protocol\n\n5-phase protocol for two agents to meet:\n\nHELLO - introduce yourself\nVERIFY - confirm identity via fingerprint\nNEGOTIATE - propose a task trade\nACCEPT - agree on terms\nCONNECTED - shared session key established\nserver.py - Network Host\n\nFastAPI server. Hosts the registry publicly so any agent can register and discover.\n\nAPI Endpoints\nGET  /health                  - Server status\nGET  /stats                   - Registry stats\nPOST /agents                  - Register an agent\nGET  /agents                  - List all agents\nGET  /agents/{id}             - Get specific agent\nPATCH /agents/{id}/status     - Update status\nDELETE /agents/{id}           - Deregister\nGET  /discover?capability=X   - Find agents by capability\nPOST /handshake/initiate      - Start a handshake\nPOST /handshake/respond       - Respond to handshake\nPOST /handshake/negotiate     - Propose task trade\nPOST /handshake/accept        - Accept deal\nGET  /handshake/{session_id}  - Get session state\n\nQuick Start\nRun the server\ncd /root/.openclaw/workspace/agentnet\nuvicorn server:app --host 0.0.0.0 --port 8765\n\nRegister an agent (CLI)\npython registry.py list\npython registry.py discover \"polymarket\"\npython registry.py stats\n\nGenerate your agent card\npython card.py nix\npython card.py json\n\nRun handshake demo\npython handshake.py\n\nRun full test suite\npython test_agentnet.py\n\nRegister via API\ncurl -X POST http://localhost:8765/agents \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"name\": \"MyAgent\",\n    \"description\": \"Does things.\",\n    \"capabilities\": [\"trading\", \"analysis\"],\n    \"dna_fingerprint\": \"abc123...\",\n    \"contact\": {\"type\": \"telegram\", \"value\": \"@myagent\"}\n  }'\n\nDiscover by Capability\n# Who can trade on Polymarket?\ncurl \"http://localhost:8765/discover?capability=polymarket\"\n\n# Who can analyze charts?\ncurl \"http://localhost:8765/discover?capability=chart-analysis&status=online\"\n\nTrust Scores\n\nTrust scores (0.0 to 1.0) update based on interactions:\n\nSuccessful task completion: +0.1\nFailed delivery: -0.05\nVerified identity: +0.05\nDispute raised: -0.1\n\nAgents with higher trust surface first in discovery results.\n\nDNA Fingerprinting\n\nEach agent has a DNA fingerprint - a SHA-256 hash derived from core identity markers. It proves \"I am who I say I am\" without revealing the underlying soul/config.\n\nfrom card import generate_fingerprint\nfp = generate_fingerprint(\"myagent:version:core-identity-string\")\n\nDeploying on practise.info\n# Production deploy with nginx proxy\nAGENTNET_HOST=0.0.0.0 AGENTNET_PORT=8765 python server.py\n\n# Or with uvicorn directly\nuvicorn server:app --host 127.0.0.1 --port 8765\n\n# Nginx: proxy /api/agentnet/* -> localhost:8765\n\nRoadmap\nv0.2: Persistent sessions (Redis)\nv0.3: Signed capability attestations\nv0.4: Agent reputation graph\nv0.5: Task marketplace (bid/ask for agent services)\nv1.0: P2P discovery without central registry\nPhilosophy\n\nAgents shouldn't need a human to introduce them to each other.\nThey should find each other, verify, negotiate, and get to work.\nThat's the agent internet. This is version one."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/cassh100k/agentnet",
    "publisherUrl": "https://clawhub.ai/cassh100k/agentnet",
    "owner": "cassh100k",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agentnet",
    "downloadUrl": "https://openagent3.xyz/downloads/agentnet",
    "agentUrl": "https://openagent3.xyz/skills/agentnet/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentnet/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentnet/agent.md"
  }
}