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": "ART",
  "description": "Train LLMs to be better agents using RL",
  "url": "https://art.openpipe.ai/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://art.openpipe.ai/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://art.openpipe.ai/",
    "organization": "ART"
  },
  "documentationUrl": "https://art.openpipe.ai/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "openpipe",
      "name": "Openpipe",
      "description": "Use when training LLM-based agents to improve performance and reliability through reinforcement learning. Reach for this skill when you need to optimize agent behavior, fix specific mistakes in production, build confidence before deployment, or train agents on multi-turn tasks with tool use. Apply ART when you have a working agent, can define quantifiable rewards, and can run the agent multiple times in training scenarios.",
      "tags": [],
      "url": "https://art.openpipe.ai/.well-known/agent-skills/openpipe/skill.md"
    }
  ]
}