Hermes

Hermes

v2026.6.19

Category: AI & Machine Learning

#ai#self-hosted#docker#hermes

Overview

Hermes is an open agent runtime from Nous Research, exposing an OpenAI-compatible gateway API and a supervised web dashboard for building and running AI agents.

Primary Use Cases

1

Run private, self-hosted AI models and inference pipelines for Hermes without sending data to third-party clouds.

2

Integrate with local LLM runners (Ollama, vLLM) and OpenAI-compatible API endpoints.

3

Build custom agentic workflows, document retrieval systems (RAG), and embeddings pipelines.

Key Features

  • Hardware acceleration support for CPU and GPU container workloads
  • Vector database compatibility for semantic search and knowledge bases
  • Modern web UI with multi-user access and API key management
  • 1-click Docker deployment with automated HTTPS reverse proxy in tug.sh

Container Specification

Docker Image

hermes:latest

Default Version

v2026.6.19

SSL & Domain Routing

Automated Let's Encrypt (Caddy / Traefik)

Persistent Volumes

Managed host volume mounts

How to Deploy Hermes with tug.sh

1

Connect your Linux server

Run the 1-line tug.sh agent install command on any Ubuntu, Debian, or Rocky Linux VPS.

2

Select Hermes from the Marketplace

Pick your domain name, configure custom environment variables if needed, and choose your persistent storage folder.

3

Click Deploy & Go Live

tug.sh pulls the container, sets up HTTPS certificates, configures the reverse proxy, and boots the service in under 60 seconds.