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": "TrueForge",
  "description": "Open-source agent harness \u2014 MCP tools, skills, sandboxing, approvals, and subagents.",
  "url": "https://trueforge.dev/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://trueforge.dev/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://trueforge.dev/",
    "organization": "TrueForge"
  },
  "documentationUrl": "https://trueforge.dev/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "trueforge",
      "name": "Trueforge",
      "description": "Use when building, configuring, or deploying AI agents with the TrueForge harness. Reach for this skill when agents need to integrate MCP tools, manage long-running tasks with context optimization, handle human approvals, run code in sandboxes, or stream responses to users. Also use when setting up agent infrastructure, configuring models and connectors, or building custom agent applications via the SDK.",
      "tags": [],
      "url": "https://trueforge.dev/.well-known/agent-skills/trueforge/skill.md"
    }
  ]
}