Deploy Hermes Agent in a Proxmox LXC with Community Scripts

Wed, 07 Oct 2026 00:00:00 +0000

A small, repeatable Hermes Agent deployment for a Proxmox VE container.

Community-maintained installer

This installer is maintained by the Community Scripts project, not by Nous Research. It downloads and runs code from external sources. Review the current script and use it only on a Proxmox host you administer.

Before you start

Have the following ready:

A Proxmox VE host with capacity for a new LXC container.
A current backup or recovery plan for the host and any affected storage.
Outbound HTTPS access from the host and the new container.
A model-provider account or an approved OpenAI-compatible endpoint. Complete provider authentication only in Hermes’ interactive setup; do not put credentials in shell history or documentation.

The Community Scripts page currently lists a Debian 13 profile with 2 vCPUs, 4 GiB of RAM, and 20 GiB of disk. Treat these as installer defaults, not sizing guidance. Select the advanced installer flow when your workload needs different limits.

Self-Host Honcho on Kubernetes with LiteLLM, Redis, and GitHub Copilot

Mon, 05 Oct 2026 00:00:00 +0000

A self-hosted memory service for Hermes, with LiteLLM as the model gateway and GitHub Copilot as an upstream provider.

Illustrative configuration only

Every hostname, namespace, IP address, image version, model name, key and resource value in this guide is an example. Do not paste it into a production cluster unchanged. Create your own secrets outside Git, verify the current upstream image and model names, and apply your own network, backup and update policies.

Architecture at a glance

The request path is deliberately split into specialised layers:

AI on Samuel Matildes - Knowledge Base

Deploy Hermes Agent in a Proxmox LXC with Community Scripts

Before you start

Self-Host Honcho on Kubernetes with LiteLLM, Redis, and GitHub Copilot

Architecture at a glance