{
  "markdown": "<!-- mcp-name: io.github.vmware-skills/vmware-privateai -->\n\n# VMware Private AI (Foundation with NVIDIA) — GPU & Model-Serving Ops\n\n> **Disclaimer**: This is a community-maintained open-source project and is **not affiliated with,\n> endorsed by, or sponsored by VMware, Inc., Broadcom Inc., or NVIDIA Corporation.** \"VMware\", \"vSphere\",\n> and \"VCF\" are trademarks of Broadcom; \"NVIDIA\" is a trademark of NVIDIA. Source is auditable at\n> [github.com/vmware-skills/VMware-PrivateAI](https://github.com/vmware-skills/VMware-PrivateAI) under the MIT license.\n\n> **Status: pre-MVP skeleton (2026-08-06).** Skill #15 of the VMware family. Manages the **GPU / AI-infrastructure\n> layer** of VMware Private AI Foundation with NVIDIA (PAIF-N) on vSphere 9.x / VCF 9.1 — GPU host/device\n> inventory, vGPU & DirectPath profiles, GPU consumers and utilization, vGPU assignment, and Private AI\n> Service (PAIS) model serving. Independent 1.x version line.\n\nCompanion of **vmware-aiops** (the vCenter VMs behind AI workloads), **vmware-vks** (GPU-enabled Kubernetes),\nand **vmware-monitor** (read-only health). This skill is the GPU lens over all three.\n\nEvery API path is verified against official Broadcom/NVIDIA docs before use (see\n`tests/eval/spec/privateai_endpoints.py`) — no endpoints written from memory.\n",
  "bytes": 1301,
  "sha": "20c3a45982a367f399da3a876df85f687d0ba18e6bd1cb52b8ef9d305b7ff6b1",
  "repo_slug": "vmware-skills/vmware-privateai",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_vmware_skills_vmware_privateai_f4311670/readme"
}