Hosting Guide

16 ways to host Hermes Agent — 6 VPS providers, 6 self-hosted options, 6 free tiers. Reviews, specs, and setup guides for every budget.

16
Total Options
6
VPS
6
Self-Hosted
6
Free Options
☁️ VPS Providers

Hetzner Cloud CX

VPS
★★★★★
€3.49 /month (CX22)

Best price-to-performance ratio in the VPS market. ARM and x86 options. Hermes runs perfectly on their cheapest CX22 instance. German hosting, excellent network.

Specs: CX22: 2 vCPU, 4GB RAM, 40GB SSD. CX32: 4 vCPU, 8GB RAM, 80GB SSD for €5.99
🎯 Best for: Best overall value. CX22 is enough for Hermes + API models. CX32 if you want Ollama with 3B-7B models.
Pros
  • Best price/performance in market
  • ARM instances cheaper
  • Excellent network
  • Simple control panel
  • EU and US datacenters
Cons
  • No managed support on basic plans
  • Limited to EU/US regions
  • Some IPs flagged by APIs initially
Setup guide
Sign up at hetzner.com → create project → add SSH key → create CX22 VM (Ubuntu 24.04) → ssh in → curl install hermes → setup provider → run gateway
☁️ VPS Providers

Hetzner Cloud CAX (ARM)

VPS
★★★★★
€2.99 /month (CAX11)

ARM-based instances at even lower prices. CAX11 starts at €2.99 for 2 vCPU, 4GB RAM. Perfect for running Hermes 24/7 on a budget.

Specs: CAX11: 2 ARM vCPU, 4GB RAM, 40GB SSD. CAX21: 4 vCPU, 8GB RAM for €5.99
🎯 Best for: Cheapest reliable 24/7 Hermes host. CAX11 for API-only use, CAX21 for local 3B models.
Pros
  • Cheapest reliable VPS
  • Same great network as x86
  • ARM efficiency = lower power
  • €2.99 is hard to beat
Cons
  • ARM-only software compatibility checks needed
  • No bare metal ARM option
  • Less CPU perf than x86 for model inference
Setup guide
Same as CX series — select ARM image when creating VM. Ubuntu 24.04 ARM works perfectly.
☁️ VPS Providers

DigitalOcean Basic Droplet

VPS
★★★★☆
$6 /month (Basic 2GB)

Developer-friendly VPS with excellent documentation and UI. Slightly pricier than Hetzner but easier to use. Good for beginners.

Specs: Basic: 1 vCPU, 2GB RAM, 50GB SSD, 1TB transfer. Premium: 2 vCPU, 4GB RAM, 80GB SSD for $12
🎯 Best for: Beginners who want an easy control panel. Good docs and community. 2GB plan works for Hermes + API models.
Pros
  • Excellent documentation
  • Clean, intuitive dashboard
  • Good community tutorials
  • Team management features
  • Wide region selection
Cons
  • More expensive than Hetzner
  • 2GB RAM at $6 vs 4GB at €3.49
  • Transfer overage costs
  • No ARM option
Setup guide
DigitalOcean → Create Droplet → Ubuntu 24.04 → add SSH key → create → ssh in → install Hermes → configure gateway
☁️ VPS Providers

Linode / Akamai Nanode

VPS
★★★★☆
$5 /month (Nanode 1GB)

Akamai's cloud (formerly Linode). Solid mid-range option with good network and simple pricing. Their Nanode 1GB is cheap but minimal.

Specs: Nanode: 1 vCPU, 1GB RAM, 25GB SSD, 1TB transfer. Shared 4GB: 2 vCPU, 4GB RAM, 80GB SSD for $12
🎯 Best for: Shared 4GB plan is the sweet spot for Hermes. 1GB Nanode is too tight for anything beyond basic use.
Pros
  • Simple pricing
  • Good network quality
  • Long-established provider
  • Excellent support
  • API-first design
Cons
  • 1GB Nanode is underpowered
  • Pricier than Hetzner for equivalent spec
  • No ARM instances
  • Backups cost extra
Setup guide
Linode → Create Linode → Ubuntu 24.04 → choose plan → add SSH key → deploy → SSH in → install Hermes
☁️ VPS Providers

Vultr Cloud Compute

VPS
★★★★☆
$6 /month (2GB plan)

Global provider with 32+ datacenter locations. Good for low-latency connections worldwide. Regular plans are competitively priced.

Specs: 2GB: 1 vCPU, 2GB RAM, 55GB SSD, 2TB transfer. 4GB: 2 vCPU, 4GB RAM, 80GB SSD for $12
🎯 Best for: Best for geographic diversity — deploy Hermes close to your API provider or users. 4GB plan for local models.
Pros
  • 32+ datacenter locations (best global coverage)
  • Competitive pricing
  • ISO library
  • S3-compatible object storage
  • One-click apps
Cons
  • Slightly slower network than Hetzner
  • Support response times vary
  • Bare metal is expensive
Setup guide
Vultr → Deploy Server → choose location closest to you → Ubuntu 24.04 → 2GB plan → SSH key → deploy → SSH in → install Hermes
🆓 Free Tier

Oracle Cloud Free Tier

Cloud
★★★★☆
$0 /month (always free)

Always-free ARM instance — 4 vCPU, 24GB RAM, 200GB SSD. No time limit, no credit card required for some tiers. The best free hosting for Hermes.

Specs: 4 ARM vCPU (Ampere A1), 24GB RAM, 200GB SSD. Also includes 10GB object storage.
🎯 Best for: Best free option by far. 24GB is enough for 13B+ local models via Ollama. Always-free, no expiration.
Pros
  • 24GB RAM completely free
  • 4 ARM vCPU cores
  • 200GB boot volume
  • No time limit (always free)
  • Enough for 13B local models
Cons
  • Oracle signup can be finicky
  • Limited availability in some regions
  • ARM only on free tier
  • Support is paid-only
  • Oracle dashboard is complex
Setup guide
Sign up at oracle.com/cloud/free (may need credit card for verification) → create VM → select Ampere A1 shape → Ubuntu 24.04 → SSH in → install Hermes + Ollama
☁️ VPS Providers

AWS Lightsail

VPS
★★★☆☆
$5 /month (512MB RAM)

Amazon's simplified VPS. Easier than EC2 but more expensive. Good if you're already in the AWS ecosystem. Predictable pricing.

Specs: $5: 512MB RAM, 1 vCPU, 20GB SSD, 1TB transfer. $10: 1GB RAM, 1 vCPU, 40GB SSD. $20: 2GB RAM, 1 vCPU, 60GB SSD
🎯 Best for: Only if you're already in AWS ecosystem. The $5 plan is too small — get the $20 (2GB) plan minimum for Hermes.
Pros
  • Part of AWS ecosystem
  • Simple pricing (no surprise bills)
  • Good documentation
  • Built-in monitoring
  • Managed backups available
Cons
  • More expensive than Hetzner/DigitalOcean
  • 512MB $5 plan is useless
  • 1 vCPU even on higher plans
  • Smaller SSD than competitors
Setup guide
AWS Console → Lightsail → Create instance → Linux/Unix → Ubuntu 24.04 → $20 plan → create → SSH via browser → install Hermes
🏠 Self-Hosted

Raspberry Pi 5

SBC
★★★★☆
$80 (board only, 8GB model)

Low-power, always-on single-board computer. Pi 5 (8GB) runs Hermes + Ollama 3B models well. Silent, cheap to run, great for learning.

Specs: ARM Cortex-A76 (4 core), 8GB LPDDR4X RAM, microSD or NVMe via HAT, USB 3.0, Gigabit Ethernet
🎯 Best for: Low-power always-on Hermes. Great for gateway + API-only use. Can run 3B models via Ollama on 8GB model.
Pros
  • Very low power (~5-15W)
  • Silent (fanless with heatsink)
  • $60-80 one-time cost
  • Great learning platform
  • GPIO for home automation integration
Cons
  • ARM64 — check software compatibility
  • Limited RAM for local models
  • microSD can be slow (use NVMe)
  • No GPU for local inference
  • Network via USB Ethernet on older models
Setup guide
Get Pi 5 + 32GB+ microSD (or NVMe HAT) → flash Ubuntu Server 24.04 LTS → enable SSH → `curl ... | bash` install Hermes → configure gateway → let it run 24/7
🏠 Self-Hosted

Intel NUC / Mini PC

Mini PC
★★★★★
$150-300 (used/refurbished)

Small form-factor x86 PC. Much more powerful than Pi for local models. Can run 7B-13B models with decent speed. Silent or near-silent.

Specs: Intel i3/i5/i7 (8th-13th gen), 8-32GB RAM, 256GB+ NVMe SSD. Fanless cases available for some models.
🎯 Best for: Best self-hosted option. NUC with 16GB RAM can run 7B models comfortably. Refurbished units are excellent value.
Pros
  • Full x86 compatibility
  • Can run 7B-13B models
  • Silent or near-silent
  • Low power (~15-30W)
  • Small footprint
  • Refurbished units are cheap
Cons
  • Higher upfront cost than Pi
  • Need to source used/refurbished
  • Some models have fan noise
  • Not as portable as Pi
Setup guide
Get a used NUC (eBay: $150 for 8th gen i5) → add NVMe SSD + RAM → install Ubuntu Server 24.04 → SSH in → install Hermes → install Ollama → configure gateway + cron jobs
🏠 Self-Hosted

Old Laptop / Repurpose

Repurpose
★★★★★
$0 (free, you already own it)

Best bang for buck — that old laptop in a drawer is a perfect Hermes server. Built-in UPS (battery), WiFi, keyboard for emergency access.

Specs: Any laptop with 8GB+ RAM, SSD preferred. 4GB is usable for API-only. Intel 8th gen or newer recommended.
🎯 Best for: Ultimate budget option — it's free. Even a 5-year-old laptop is overkill for Hermes + API models.
Pros
  • Completely free (you own it)
  • Built-in UPS (battery backup)
  • WiFi + Ethernet
  • Can also serve as media server
  • Good performance (i5/i7)
Cons
  • Takes up desk space
  • Screen is wasted (headless)
  • Fan noise
  • Older models use more power
  • Not as "clean" as a dedicated solution
Setup guide
Install Ubuntu Server (or keep existing OS) → plug in Ethernet for reliability → close lid (configure to stay on when closed) → install Hermes → install Ollama if desired → run gateway → forget it exists
🏠 Self-Hosted

Home Server / Tower

Server
★★★★☆
$300-800 (build or buy)

Dedicated server hardware at home. Overkill for Hermes alone but great if you're running other services (NAS, Plex, Home Assistant).

Specs: Any modern CPU, 16-64GB RAM, SSD storage. Can run 13B-70B models locally. Supports GPU inference with NVIDIA card.
🎯 Best for: Power users who already run a home server. Hermes is a lightweight addition to an existing Proxmox/Docker setup.
Pros
  • Maximum performance
  • GPU support for local models
  • Run with other services
  • Full control over hardware
  • Can handle 70B models with decent GPU
Cons
  • Expensive
  • High power consumption
  • Loud (fans)
  • Takes up space
  • Overkill for Hermes alone
Setup guide
Install Proxmox or Ubuntu Server → create VM or Docker container for Hermes → install via script → configure gateway → add to startup → manage alongside other services
🏠 Self-Hosted

NAS (Synology / QNAP)

NAS
★★★☆☆
$0 (if you already have a NAS)

Run Hermes on your existing NAS via Docker. Most modern NAS units have enough power. Uses storage you already have.

Specs: Intel Celeron or better, 4GB+ RAM, Docker support. Synology DS220+ or better recommended. QNAP TS-2xx or better.
🎯 Best for: If you already run a NAS, adding Hermes is free. Good for gateway + cron jobs. Not for local models.
Pros
  • Uses existing hardware
  • 24/7 operation (NAS runs anyway)
  • RAID storage redundancy
  • Low additional power use
Cons
  • Limited RAM (4-8GB typical)
  • Underpowered CPU
  • No GPU
  • Docker on NAS can be finicky
  • Not for local models
Setup guide
NAS → Package Center → install Docker/Container Manager → pull hermes-agent image → create container with volume mounts for config → set up port/gateway → start
⚡ Serverless

Google Cloud Shell

Cloud
★★☆☆☆
$0 (free, 1-hour sessions)

Free browser-based terminal with 5GB home dir. Great for trying Hermes instantly with zero setup. Not persistent (times out after 1 hour).

Specs: Free: 1 vCPU, 2GB RAM (approx), 5GB persistent disk. Pre-installed with Python, Node, git.
🎯 Best for: Quick testing and evaluation. Not for production — sessions time out. Good for "try before you buy" without installing anything.
Pros
  • Completely free
  • No installation on your machine
  • Pre-installed tools
  • Accessible from any browser
Cons
  • 1-hour session limit (not persistent)
  • No gateway (ports not exposed)
  • Limited RAM
  • Not suitable for production
  • Google account needed
Setup guide
Go to shell.cloud.google.com → `curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash` → `hermes setup` → try it → session ends in 1 hour
⚡ Serverless

Modal

Cloud
★★★☆☆
Free tier ($30/month free credits)

Serverless GPU/CPU compute. Hermes has native Modal support as a terminal backend. Good for burst inference with GPU. Free tier available.

Specs: Free tier: $30/month credits. CPU and GPU instances. Pay-as-you-go beyond free credits. No always-on — cold starts.
🎯 Best for: Burst inference with GPU access. Not for persistent gateway. Good for running large models (70B) on demand.
Pros
  • GPU access on free tier
  • No server management
  • Pay only for compute used
  • Native Hermes support
Cons
  • Cold starts (~10-20s)
  • No persistent gateway
  • Credit-based, not for 24/7 use
  • Learning curve for Modal SDK
Setup guide
Sign up at modal.com → install modal CLI → authenticate → configure Hermes with terminal backend: `modal` → `hermes chat -q "..."` runs on Modal infra
⚡ Serverless

Daytona

Cloud
★★★☆☆
Free tier (limited)

Development environment manager with Hermes support. Creates isolated workspaces with Hermes pre-installed.

Specs: Cloud-hosted dev environments. Pre-configured Hermes support. Git integration. Workspace-based.
🎯 Best for: Development workflows where you need Hermes alongside your code. Less suited for persistent gateway hosting.
Pros
  • Pre-configured Hermes support
  • Git-integrated workspaces
  • Good for development
Cons
  • Not for 24/7 gateway
  • Free tier has limits
  • Workspace-based (not always-on)
Setup guide
daytona.io → sign up → create workspace → select Hermes template → workspace starts with Hermes ready → use via terminal
🏠 Self-Hosted

Hardware: Absolute Cheapest 24/7

SBC
★★★☆☆
$15-30 (one-time, used hardware)

Run Hermes on an old Android phone with Termux + Linux Deploy. Or a $20 used thin client from eBay. The absolute lowest-cost always-on setup.

Specs: Any old Android phone (4GB RAM+) or thin client (Wyse, HP t620). ARM or x86. USB power for the phone.
🎯 Best for: Absolute budget builds. $20 thin client from eBay + $5 USB power adapter = cheapest 24/7 Hermes server.
Pros
  • Extremely cheap
  • Low power (phone: 2-5W)
  • Teaches Linux skills
  • Repurposes e-waste
Cons
  • Limited performance
  • Setup is more involved
  • Phone battery swelling risk if always plugged
  • Thin clients have weak CPUs
Setup guide
Thin client: Install Linux (Debian/Ubuntu) on internal storage or USB → SSH → install Hermes. Android: Install Termux → `pkg install python` → pip install hermes-agent.
🔍

No hosting options match your search. Try a different filter or keyword.