Paperclip AI
DeepSeek
Coolify
Dokploy
WireGuard VPN
Plesk Servers
cPanel Servers
Blockchain NodesHermes Solo
$13.20/ month
- vCPU
- 4
- RAM
- 8 GB
- Storage
- 100 GB SSD
- Fits
- One person
AI agent hosting
Your own Hermes Agent, running on your server.
Hermes Agent is an open-source AI agent from Nous Research that remembers past sessions, schedules work and uses tools to browse, handle files and run code. We deliver a server with it installed, so you only connect a model and your integrations.
- From $13.20 / month
- Hermes Agent preinstalled
- Up to 96 GB RAM
- Istanbul or Nuremberg
- vCPU cores per server
- 4 to 18
- RAM for the agent and local models
- 8 to 96 GB
- SSD storage on the largest size
- 600 GB
- SSH access to the whole server
- Root
Hermes Agent Hosting
Pick a size for your agent
Larger sizes leave room for more subagents and for a local model next to the agent.
Hermes Pro
$18/ month
- vCPU
- 6
- RAM
- 12 GB
- Storage
- 200 GB SSD
- Fits
- Daily heavy use
Hermes Team
$60/ month
- vCPU
- 12
- RAM
- 48 GB
- Storage
- 400 GB SSD
- Fits
- Small teams
Hermes Scale
$117.60/ month
- vCPU
- 18
- RAM
- 96 GB
- Storage
- 600 GB SSD
- Fits
- Parallel pipelines
Prices in USD, billed monthly unless stated otherwise. Need a different size? Ask for a custom configuration.
What you get
Built in, not bolted on.
Agent installed for you
The server arrives with Hermes Agent set up. Point it at a model, add your integrations and start the first session.
Scheduled jobs
Set recurring tasks such as weekly digests or end-of-day reports, and the agent runs them on its own while you are offline.
Memory across sessions
Past conversations and notes stay on the server disk, so today's session can build on yesterday's work.
Subagents and tools
Hand work to subagents that browse the web, read and write files and run code at the same time.
Private by default
Prompts, memory and outputs stay on a server only you can reach. Keep the web UI behind an SSH tunnel or a Tailscale network.
Grow without starting over
Move to a larger size when teammates or subagents join. The agent keeps its memory and schedules.
Use cases
What teams run on it.
-
01
Coding assistant
Pair the agent with a coding model for reviews, refactors and small features on a private repository.
-
02
Team assistant
Put the agent behind an internal app or VPN so colleagues can use it without prompts leaving your network.
-
03
Research and notes
Collect sources, summarize long documents and keep the findings in memory for the next session.
-
04
Automated reports
Schedule jobs that gather data and write a summary every morning or at the end of each week.
How it works
Three steps to running.
-
01
Choose a size
Pick a plan by how many people and subagents will use the agent, and choose Istanbul or Nuremberg.
-
02
Get your server
We provision the server with Hermes Agent installed and send you the SSH details.
-
03
Connect and run
Point the agent at a model, add integrations and open the web UI through an SSH tunnel to check the setup.
Questions
Hermes Agent Hosting, answered.
What is the difference between Hermes models and Hermes Agent?
Hermes is a family of open-weights language models from Nous Research. Hermes Agent is the runtime around a model: memory, scheduling, subagents and tools. You can swap the model without rebuilding the agent.
Which model does the agent use?
Your choice. Run an open model locally with Ollama on the same server, or connect a hosted model through its API.
How do I reach the agent?
From the command line over SSH, or through the Hermes web UI opened over an SSH tunnel. Add Tailscale if you want it on a private mesh network.
Can I update Hermes from GitHub?
Yes. The Hermes repositories are open source, so you can pull new releases, add recipes or run your own fork. You keep root access to the server.
Can I move to a bigger plan later?
Yes. Resize when the workload grows. The agent keeps its memory and scheduled jobs.
More app hosting
Often used together.
n8n Hosting
Your own n8n instance on a private server, installed and ready. Unlimited workflows for one flat price.
From $13.20 / month
Explore
Nextcloud Hosting
Your own private cloud for files, calendars and contacts. Nextcloud preinstalled, unlimited users.
From $13.20 / month
Explore
OpenClaw Hosting
A personal AI agent on your own server, reachable from WhatsApp, Telegram, Slack and more. Preinstalled.
From $13.20 / month
ExploreTalk to an engineer
Not sure which size fits?
Tell us what you want to run. An engineer suggests a configuration and sends you a written price.