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": "Cerebrium",
  "description": "Cerebrium developer documentation for real-time and production AI workloads. Learn how to deploy low-latency inference APIs, voice agents, multi-region apps, serverless GPUs and CPUs, and workloads that need strong cold-start and scaling performance.",
  "url": "https://cerebrium.ai/docs/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://cerebrium.ai/docs/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://cerebrium.ai/docs/",
    "organization": "Cerebrium"
  },
  "documentationUrl": "https://cerebrium.ai/docs/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "cerebrium",
      "name": "cerebrium",
      "description": "Use for any Cerebrium task: deploying Python code to serverless GPU or CPU, writing or fixing cerebrium.toml, choosing hardware and regions, calling deployed endpoints (REST, streaming, WebSocket, async), autoscaling and concurrency, cold starts, secrets, CI/CD, and debugging a build or a running app from the terminal. Covers the cerebrium CLI, configuration defaults the API actually applies, accepted GPU identifiers with per-plan limits, and troubleshooting.",
      "tags": [],
      "url": "https://cerebrium.ai/docs/.well-known/agent-skills/cerebrium/skill.md"
    }
  ]
}