skills.rest
paarths-collab
paarths-collabCOMMUNITY
Explore all skills by this author →
GitHub

hermes-model

Configure remote Hermes model and provider settings over SSH with rollback.

13|1|Updated Jun 1, 2026
Search Tags:#llm#api key#ssh#smoke test#model configuration#hermes#provider setup
One-click install
npx skills add https://github.com/paarths-collab/hstack --skill hermes-model
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hermes-model
Source: https://github.com/paarths-collab/hstack/tree/main/skills/hermes-model
Command: npx skills add https://github.com/paarths-collab/hstack --skill hermes-model

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of configuring a self-hosted Hermes agent with the right provider and model on a remote VPS, while avoiding broken headless setup flows and late API-key failures.

Core Features & Use Cases

  • Remote Model Setup: Sets the LLM provider and model over SSH on the VPS where Hermes runs.
  • Safe Validation: Verifies Hermes is installed, checks idempotency, reloads the gateway correctly, and smoke-tests inference to confirm the key works.
  • Reliability Guardrails: Detects degraded capabilities, requires a frontier model with sufficient context, and includes rollback steps for failed configuration changes.

Quick Start

Configure the Hermes model and provider on the remote VPS, then run a live inference smoke test to verify the API key, gateway, and context window are working.

Frequently Asked Questions about hermes-model

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure a remote LLM provider and API key on a VPS via SSH?▼

To configure a remote LLM provider, this Skill applies SSH-first deployment to set up the API key and model configuration on a VPS, then reloads the gateway and runs a live inference smoke test to verify the setup.

What is required for a non-interactive Hermes model setup on a remote server?▼

A non-interactive Hermes model setup requires a valid frontier LLM API key, a model with at least 64K context, and an SSH connection to the self-hosted VPS to execute the provider switching and gateway reload.

Can I use this to switch LLM providers for agents managed by Claude Code or Cursor?▼

Yes, you can switch LLM providers and configure models for Hermes agents managed by Claude Code, Codex, Cursor, Gemini CLI, or Hermes itself by applying the remote SSH setup and gateway reload.

What happens if the live inference smoke test fails after changing the model configuration?▼

If the live inference smoke test fails, the Skill executes rollback steps to revert the failed configuration changes, ensuring the Hermes agent returns to its previous working state safely.

Why does my headless VPS deployment fail during late API-key validation?▼

Headless VPS deployment fails late because the API key is not validated early enough; this Skill avoids broken setup flows by verifying Hermes installation and running a live inference smoke test to confirm the key works.

Related Skills

Explore More Software Engineering Skills→
Avi977Avi977

vps-deploy

Automate GitHub-to-VPS deployment with SSH keys, workflows, and health checks.

Community
Advanced
runningdev9998runningdev9998
12

clawra-selfie

Generate and send personalized images via xAI's Grok Imagine model on fal.ai.

Community
Intermediate
paarths-collabpaarths-collab
13

integration-hubspot

Connect HubSpot CRM data to a self-hosted Hermes agent via SSH.

Community
Advanced
paarths-collabpaarths-collab
13

integration-segment

Connect Segment to a self-hosted Hermes agent via SSH.

Community
Advanced