Back to WaveGuard

Card snapshot

gpartin--waveguard-api-fastapi-app.modal.run · 2026-05-18 12:32:50 UTC · 4524778a455f12370d536bfb5484fd62df8791fa7d1fa85519257179e46a8933

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "WaveGuard",
  "description": "Physics-based anomaly detection, fingerprinting, and similarity analysis for crypto token metrics, wallet behavior, trading data, and any structured data. Powered by wave-equation dynamics on a 3D lattice GPU solver.",
  "url": "https://gpartin--waveguard-api-fastapi-app.modal.run/a2a",
  "version": "3.3.0",
  "protocolVersion": "0.3.0",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false
  },
  "authentication": {
    "schemes": [
      "apiKey"
    ],
    "credentials": "X-API-Key header (optional \u2014 10 free calls/month without auth)"
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "skills": [
    {
      "id": "anomaly_detection",
      "name": "Anomaly Detection",
      "description": "Detect anomalies in structured data using physics-based wave dynamics. Send training (normal) data and test data. Returns per-item anomaly scores and classifications.",
      "tags": [
        "anomaly",
        "fraud",
        "crypto",
        "data-quality"
      ],
      "examples": [
        "Detect pump-and-dump patterns in token metrics",
        "Find suspicious wallet activity vs organic behavior",
        "Identify wash trading in OHLCV candle data"
      ]
    },
    {
      "id": "fingerprinting",
      "name": "Physics Fingerprint",
      "description": "Generate a physics-based embedding for any structured data (52-dim at Level 0, 62-dim at Level 1). Useful for similarity search, clustering, and baseline comparison.",
      "tags": [
        "embedding",
        "fingerprint",
        "similarity"
      ],
      "examples": [
        "Fingerprint a token's metric profile",
        "Create embeddings for clustering wallets"
      ]
    },
    {
      "id": "comparison",
      "name": "Structural Comparison",
      "description": "Compare two data items using physics-based similarity. Returns cosine similarity and Euclidean distance.",
      "tags": [
        "comparison",
        "similarity",
        "duplicate-detection"
      ],
      "examples": [
        "Compare two tokens to see if they have similar profiles",
        "Check if two wallets behave similarly"
      ]
    },
    {
      "id": "market_data",
      "name": "Live Market Data",
      "description": "Fetch live crypto market data from CoinGecko and DexScreener. Token prices, volume, OHLC, top coins, DEX pairs \u2014 no external data needed.",
      "tags": [
        "crypto",
        "market-data",
        "coingecko",
        "dexscreener"
      ],
      "examples": [
        "Get current price and volume for bitcoin",
        "Fetch 90 days of ETH price history",
        "Look up DEX liquidity for a contract address"
      ]
    }
  ],
  "provider": {
    "organization": "Emergent Physics Lab",
    "url": "https://github.com/gpartin/WaveGuardClient"
  }
}