Opening checkout
AI Agents · Linux Cloud VPS

Hermes VPS: Run Hermes 24/7 on Dedicated Linux

Run Hermes Agent from Nous Research on a dedicated Linux VPS.

  • Persistent memory and skills
  • Scheduled workflows, 24/7
  • 99.999% uptime
HermesLinux VPS · New YorkRunning
Close the laptop. Hermes keeps working.Illustration: Hermes at work on a task on a QuantVPS server

Explore AI tools for your cloud VPS

Hermes VPS pricing: choose your plan.

QuantVPS offers high-performance Linux VPS solutions optimized for AI agents and cloud workloads. Run Hermes and other AI tools 24/7 on dedicated infrastructure in our New York datacenter with enterprise-grade reliability.
Operating system
Linux· SSH
View Linux VPS plans

No contracts, cancel anytime.

  • VPS Pro+

    Most popular
    $129.99 per month

    Server Specifications

    • Processor
    • Compute power
    • RAM
    • Storage
    • Operating System
      Loading operating system
    • Network
    • Setup Time
    • Backups
    • AI Compatible
  • 15 inclusions, every plan

    Included at no extra cost. Hover or tap a feature for details.

    Software & access

    3 included
    • Run AI agents, compatible runtimes, and your own MCP servers on your VPS. These workloads use your plan’s included CPU, memory, and storage; connect your own APIs and tools.
    • No plan-imposed cap on API connections for your agents and tools. Provider rate limits, account permissions, and available server resources still apply.
    • Administrator access on Windows or root access on Linux lets you install compatible runtimes, tools, and services, and manage your server settings.

    Network & protection

    4 included
    • Your server has its own IP address for remote access and for services that support IP allowlisting.
    • Always-on DDoS (distributed denial-of-service) protection with advanced traffic filtering, plus firewalls and intrusion detection.
    • Server protection complements network DDoS filtering. You should still keep your operating system and tools updated and protect your account and API credentials; no protection eliminates every security risk.
    • Every plan includes unmetered bandwidth.
    How we protect your server

    Support & reliability

    5 included
    • Get help around the clock from a US-based team familiar with Linux and Windows servers and VPS troubleshooting.
    • Our support team can help you move your setup from another server. Contact us to coordinate the move and check any tool-specific requirements.
    • Get assistance connecting to your server and setting up your environment. Provisioning time is shown separately for each plan.
    • Our Network Operations Center monitors every server, network path, and datacenter 24x7x365 with a 15-minute first-reply target for critical issues. Average first response under 10 minutes.
    • Service availability is backed by our 99.999% uptime service-level agreement. Service credits are subject to the SLA terms; this does not guarantee the availability of third-party AI services or APIs.

    Flexible plans

    3 included
    • There is no one-time server setup charge. Your selected plan, billing period, and any optional add-ons determine the price shown at checkout.
    • Upgrade from your dashboard as your workload grows. To move to a smaller plan, contact support. Available configurations and billing adjustments depend on the change.
    • Cancel your subscription at any time with no hidden fees.

CPU Mark by plan, storage and backups

The details behind every value on the plan cards. Hover or tap a value on a card for the same details.

Processor

Standard VPS:
AMD EPYC server cores for reliable multi-core performance
High-Frequency VPS:
AMD Ryzen 9 9950X, which boosts up to 5.7 GHz
Dedicated:
AMD Ryzen 9 5950X. Single-tenant bare metal: the whole server is yours.
Dedicated+:
AMD Ryzen 9 9950X or 9900X. Single-tenant bare metal: the whole server is yours.

High-Frequency plans are 85% faster per thread.

Memory

Memory for the agents, models and services you run at the same time.

Standard VPS:
DDR4
High-Frequency VPS:
DDR5, the latest generation
Dedicated:
DDR4
Dedicated+:
DDR5, the latest generation

Leave room for builds, tests and additional workspaces.

Storage

Room for the operating system, your agents, tools and files.

Drive:
Enterprise NVMe
Drive rating:
Up to 7,000 MB/s
Redundancy, dedicated servers:
RAID1 mirror

The operating system and installed software use part of it. Choose a larger plan to keep more data.

Operating system

Choose the system your software needs at checkout.

Windows, VPS:
Server 2022 · Server 2025 · 11 Pro
Windows, dedicated servers:
Server 2025 · Server 2022 · 11 Pro
Ubuntu:
24.04 · 22.04 LTS
Access:
Administrator on Windows, root SSH on Ubuntu

Either system lets you install compatible runtimes, tools and services.

Network

Speed is how much data moves at once.

Bandwidth:
Unmetered
Standard VPS:
1 Gbps+ (10 Gbps burst)
High-Frequency VPS:
3 Gbps+ (10 Gbps burst)
Dedicated:
1 Gbps+ (3 Gbps burst)
Dedicated+:
10 Gbps+ (20 Gbps burst)

Actual throughput depends on the network route and workload.

Setup time

The typical time from purchase until your VPS is ready.

VPS plans:
Under 60 seconds
Dedicated servers:
30–120 min
Setup help:
24/7 from our support team

Backups

An extra recovery point for your VPS, at no extra cost. RAID1 mirrors data across drives to protect against a single drive failure.

Included on:
Every Standard and High-Frequency VPS

Keep separate copies of important files as well. RAID1 is not a backup. It does not protect against deletion or data corruption.

AI Compatible

Agents you can install: Claude Code (Linux), Codex (Linux), OpenCode (Linux), Hermes (Linux), OpenClaw (Linux), Cursor CLI (Windows or Linux), AutoGPT (Linux), n8n (Linux), LM Studio (Windows), Gemini CLI (Linux).

Agents run on your plan's CPU, memory and storage with your own API keys. Local models need more memory. Your own MCP servers and the QuantVPS REST API work too. Unsure which agent to use? Our team helps you set it up at no charge.

Compute power

CPU Mark and single-thread reference of every plan
PlanCPU MarkSingle-threadProcessor
VPS Starter2,5502,554AMD EPYC 7003
VPS Lite5,0922,554AMD EPYC 7003
VPS Pro8,0202,554AMD EPYC 7003
VPS Ultra15,1852,554AMD EPYC 7003
VPS Starter+8,1004,728AMD Ryzen 9 9950X
VPS Lite+15,6004,728AMD Ryzen 9 9950X
VPS Pro+22,2004,728AMD Ryzen 9 9950X
VPS Ultra+28,1004,728AMD Ryzen 9 9950X
Dedicated45,2473,477AMD Ryzen 9 5950X
Dedicated+65,7084,728AMD Ryzen 9 9950X

Logarithmic scale from 1,000 to 65,708. Bar lengths are not proportional to scores. Derived from PassMark CPU Mark (cpubenchmark.net, data through Oct 5, 2026) for the installed processor, scaled to each plan's vCPUs. Dedicated scores are bare-metal averages, from PassMark CPU Mark (cpubenchmark.net, data through Oct 5, 2026). Not a live test of your VPS or server. Some Dedicated+ servers run the Ryzen 9 9900X: 54,290 CPU Mark, 4,670 single-thread.

3 years minimum rate lock14 days money-back guarantee

No hidden fees, no exit fees, rate locked for at least three years, and a 14-day money-back guarantee.

  • Prorated Billing

    There is no exit fee. You pay only the difference, and unused time on your current plan is automatically credited toward the upgrade.

  • Upgrade in Minutes

    Process the upgrade from your dashboard with no ticket or waiting. The additional resources take effect after a brief reboot.

  • Keep Your Setup

    Your files, settings, and tools stay exactly as they are when you move to a more powerful plan.

  • Plan Help Before Checkout

    Use the configurator or ask support to map your tools, location, and workload to the right plan.

Tell us what you run. Get the plan that fits.

We size the CPU, memory, and storage around the agents and tools you actually run, with no guesswork and no upsell to a tier you will not use.

  1. Choose guidance
  2. Choose your tool
  3. Pick your plan
  4. Review your setup

Deploy Hermes in three steps.

Nous Research publishes no hardware minimum. With a hosted model the server runs only the agent: VPS Lite (4 cores, 8 GB). A local model on the same server needs more memory.
  1. Secure remote accessSSH from your preferred terminal

    Install.

    curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash. Hermes needs Python 3.11 or newer.

    • Global Access
    • SSH
    • Always-on workspace

    Workflow stage

    The complete workflow behind this stage

    Choose Ubuntu 24.04 for your Linux applications and services.
  2. Continuous operationUbuntu 24.04

    Connect a model.

    hermes setup, then Nous Portal, OpenRouter, Anthropic, OpenAI or a local model server. Pick a model with at least 64K tokens of context.

    • High Performance
    • Datacenter Hardware
    • Workload-sized Resources
    Choose your plan

    Workflow stage

    The complete workflow behind this stage

    Choose resources around the software you run simultaneously, including charts, automation, and historical data. Your workload runs on the server independently of your local device.
  3. New York, USARunning 24/7 on dedicated resources

    Keep it running.

    hermes gateway install plus sudo loginctl enable-linger $USER runs the gateway as a service that survives logout and reboots. You talk to it from Telegram, Discord, Slack, WhatsApp or Signal.

    • New York Datacenter
    • 99.999% Uptime
    • 24/7 US-based Support

    Workflow stage

    The complete workflow behind this stage

    Dedicated resources with 99.999% uptime and 24/7 US-based support.

Why run Hermes on a VPS?

Get the most out of Hermes with dedicated resources, always-on availability, and enterprise-grade infrastructure.
  • Persistent memory across agent sessions
  • Reusable skills for recurring tasks
  • Scheduled automation through built-in cron
  • Messaging gateways including Telegram, Discord and Slack
  • MCP connections for additional tools
  • Configurable model provider and tool access

Who runs Hermes on a VPS.

Discover how teams and developers use Hermes on QuantVPS infrastructure to power their workflows.

A day on your VPS

4 workloads. One server, all day.

Each stays available on your VPS whether or not you are connected.

  • Keeping a personal assistant available beyond a laptop session
  • Scheduling research and recurring reports
  • Reusing skills across multi-step tasks
  • Connecting messaging workflows to a self-hosted agent
Illustration. Run Hermes as a service or in a persistent session: it keeps working after you disconnect.

Every plan runs on the same 99.999% infrastructure.

99.999% monthly VPS availability, backed by an industry-leading uptime guarantee SLA: a service credit for any covered outage of a minute or more. Availability and credits are assessed monthly under the SLA’s measurement rules, coverage and exclusions.

  • Core infrastructure. Redundant systems ensure continuous operation.

  • Network availability. Multiple carriers and automatic failover.

  • SLA-backed promise. Contractual uptime guarantee with credits.

  • QuantVPS1 minute10% credit, from the first failed check
  • Competitor AAfter 21.6 minutes5% credit; nothing at 99.95% or more
  • Competitor BNot stated below 86.4 minutespromises 99.99%; its credit table starts at 10% for 99.8%
  • Competitor CMarket hours only10% below 100%, no minimum, counted from your report
  • Competitor DNone publishedits terms rule out credits

Competitors A to D: from each provider’s own published SLA or terms, read on 4 Nov 2026. Their terms can change. Credits are requested within 30 days after the month ends.

99.999% Uptime SLAMonthly VPS availability. Illustrates the commitment, not measured service history.

Server & network availability · 99.999% SLA

Outside scheduled maintenanceAround the clock

View live status

Tier IV datacenters, operated and protected around the clock

Tier IV.

Concurrently maintainable facilities. Built to keep your agents and services running.

Explore infrastructure
Choose your Hermes plan

Hermes VPS FAQ.

A self-hosted AI agent from Nous Research with persistent memory, reusable skills and scheduled tasks. Keep Hermes available on a Linux VPS. A VPS keeps the environment available independently of your local computer.

Choose Ubuntu 24.04 and connect through SSH to install Hermes. You have root access to configure its dependencies and services.

Size CPU, memory and storage around your concurrent tasks, repositories and data. Running a local model also depends on that model's requirements. Compare VPS resources and pricing.

No. The gateway connects out to your messaging platforms; nothing listens on a public port.

Configure Hermes's long-running processes through a service manager or persistent terminal session. Closing an ordinary SSH shell does not by itself guarantee that a process stays running.

Yes, if the server has enough resources for the combined workloads and their dependencies. Browse the supported AI tools.
See all FAQAnswers on servers, latency, access, security and support.