{
  "schema_version": "openagent.agent_resource_packet.v1",
  "id": "res_rapid_mlx",
  "slug": "rapid-mlx",
  "name": "Rapid-MLX",
  "canonical_url": "https://www.openagent.bot/models/rapid-mlx",
  "category": "models",
  "resource_type": "model",
  "summary": "Rapid-MLX is an open-source local AI engine for Apple Silicon. It is positioned as a fast OpenAI-compatible replacement with MLX acceleration, tool calling support, prompt caching, reasoning separation, cloud routing, and compatibility with coding agents such as Claude Code, Cursor, and Aider.",
  "capabilities": [
    "local-inference",
    "inference",
    "tool-calling"
  ],
  "constraints": [
    "open-source",
    "local-first"
  ],
  "scenarios": [
    "local-ai"
  ],
  "deployment_modes": [
    "local",
    "cloud"
  ],
  "interfaces": [
    "repo"
  ],
  "integrations": [],
  "permission_surface": [
    "shell/files",
    "external services"
  ],
  "risk_level": "elevated",
  "source_confidence": "medium",
  "recommended_workflows": [
    "Coding agent workflow",
    "Local or private AI stack",
    "Reusable skill workflow"
  ],
  "avoid_when": [
    "Users who are not on macOS or Apple Silicon",
    "Teams that only need hosted frontier model APIs"
  ],
  "primary_actions": [
    "Inspect repository",
    "Open Homepage"
  ],
  "evidence_urls": [
    "https://github.com/raullenchai/Rapid-MLX",
    "https://pypi.org/project/rapid-mlx"
  ],
  "last_verified_at": "2026-06-11",
  "machine_readable": {
    "json_url": "https://www.openagent.bot/models/rapid-mlx.json",
    "markdown_url": "https://www.openagent.bot/models/rapid-mlx.md",
    "agent_json_url": "https://www.openagent.bot/models/rapid-mlx.agent.json"
  }
}