Card snapshot

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": "Pixeltable Documentation",
  "description": "The only open source Python library providing declarative data infrastructure for building multimodal AI applications, enabling incremental storage, transformation, indexing, retrieval, and orchestration of data.",
  "url": "https://docs.pixeltable.com/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://docs.pixeltable.com/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://docs.pixeltable.com/",
    "organization": "Pixeltable Documentation"
  },
  "documentationUrl": "https://docs.pixeltable.com/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "pixeltable",
      "name": "Pixeltable",
      "description": "Use when building multimodal AI applications, processing images/video/audio/documents, creating RAG pipelines, building agents with tool calling, or exposing data operations as HTTP APIs. Agents should reach for this skill when working with declarative data pipelines, computed columns, embedding indexes, or serving tables over HTTP.",
      "tags": [],
      "url": "https://docs.pixeltable.com/.well-known/agent-skills/pixeltable/skill.md"
    }
  ]
}