# Provisioning Spec for Air-Gapped, Host-Isolated Local LLM Tooling

> Source: <https://forum.level1techs.com/t/provisioning-spec-for-air-gapped-host-isolated-local-llm-tooling/256313#post_1>
> Published: 2026-09-16 19:34:21+00:00

Hi all,

Got tired of seeing local LLM toolchains, agent dependencies, and scattered Python/Node environments pollute the host OS. Also wanted an architecture that doesn’t rely on cloud API black boxes or vendor-locked SaaS.

I put together a provisioning specification focused on a strict “Zero-Pollution” workflow for running local LLMs, Open WebUI, and dev agents inside isolated rootless containers while maintaining direct GPU acceleration.

`/dev/kfd` and `/dev/dri` for bare-metal AMD/ROCm acceleration without host-level driver breakage.`loginctl enable-linger`) for persistent, automated multi-container orchestration.`:Z`) boundaries.
Initial prototype started around Distrobox, but has evolved toward fully locked-down native OCI/Podman specifications for air-gapped and headless appliance setups.

Published the initial specification and compose templates to GitHub:

Curious to hear thoughts from anyone running isolated bare-metal AI workflows or hardening rootless container pipelines on Fedora/RHEL.