NEW

GPU instances are live. Use code LOCAL10 for 10% off your first month.

Deploy now
one-click templates

Deploy it
already installed

Pick a template at checkout and your server boots with everything configured: drivers, dependencies and the app itself. SSH in and use it.

Ollama

Most deployed

The easiest way to run LLMs. Pull any model with one command, serve it over an API.

From VPS Dev $12.99 (CPU) or any GPU plan
Deploy with Ollama

Open WebUI

Chat UI

A beautiful ChatGPT-style interface on top of Ollama. Multi-user, RAG, web search.

Pairs with Ollama on any plan
Deploy with Open WebUI

ComfyUI

Image

Node-based image generation. SDXL, Flux, ControlNet, upscalers, video nodes.

From RTX 4060 Ti $79 · best on 4090
Deploy with ComfyUI

n8n

Automation

Self-hosted automation with 400+ integrations. Wire your AI into everything.

From VPS Nano $6.99
Deploy with n8n

SillyTavern

Roleplay

The power-user frontend for character chat. Total privacy on your own box.

From VPS Dev $12.99 + local or API models
Deploy with SillyTavern

Whisper API

Audio

faster-whisper behind an OpenAI-compatible endpoint. Your own transcription API.

From GTX 1660 $39
Deploy with Whisper

A1111 WebUI

Image

The classic Stable Diffusion interface. Extensions for everything imaginable.

From RTX 3060 $59
Deploy with A1111

Docker + Portainer

Base

Clean Docker host with a web UI. The blank canvas for whatever stack you want.

Any plan, any distro
Deploy with Docker

code-server

Dev

VS Code in your browser, running on your server. Pair it with a local code model.

From VPS Dev $12.99
Deploy with code-server
Missing your stack? Every server ships with root access, so you can install anything. Or request a template and we will build it.