AIHostBox
Client area Deploy an app
All 57 applications
CategoriesAI assistants & chatLLM runtimesAgents & RAGGateways & LLM opsVector & dataAutomationSpeech, image & videoSearch & web agentsSupport & CXML platformMCP servers
SolutionsPrivate team chatUnlimited automationCompany knowledge AIAI gateway & observability
More PricingGuides ComparisonsToolsPrivate LLM hosting LicensingSecurity SupportClient area

SillyTavern hosting

The character-driven chat front-end, online wherever you are.

AI assistants & chatAGPL-3.0from $5.99/mo
In short

SillyTavern hosting at AIHostBox means a dedicated, single-tenant SillyTavern instance on our infrastructure: we install it, pin it to a reviewed release, put it behind TLS on your domain, back it up nightly and keep it patched. Plans start at $5.99 per month and the admin account, the data and any API keys are yours.

Character cardsLorebooksGroup chatsSampler controlMobile-friendly

SillyTavern is a front-end for character-based conversation: character cards, world info and lorebooks, group chats, prompt templates and fine-grained sampler control. It connects to commercial APIs and to local backends like Ollama, KoboldCpp and text-generation-webui.

Because it is a front-end, hosting it means your characters, chats and settings follow you between phone and desktop instead of living on one machine. Instances are private and password-protected by default.

SillyTavern hosting plans

StarterSingle user
2 GB RAM · 1 vCPU · NVMe
$5.99/mo
Order
PlusShared with friends
4 GB RAM · 2 vCPU · NVMe
$9.99/mo
Order

Every plan is a dedicated single-tenant instance with NVMe storage, nightly off-box backups, TLS and managed patching. Quarterly, semi-annual and annual terms are discounted at checkout. Model tokens are not included — you bring your own key.

How we run SillyTavern

A single Node.js container from ghcr.io/sillytavern/sillytavern with persistent config, data, plugins and third-party extension folders; there is no separate database, everything is flat files.

What we configure for you

  • listen enabled with a hostWhitelist for your domain, behind TLS
  • basicAuthMode or enableUserAccounts, so the instance is never open without a login
  • enableDiscreetLogin available if you do not want user names shown on the login page
  • Persistent /home/node/app/data volume included in the nightly off-box backup
  • Automatic upstream release updates without touching your characters or presets

Which plan fits

Starter (2 GB) is plenty for one person: SillyTavern itself is light, and the model runs elsewhere. Plus (4 GB) suits a small group on user accounts or anyone running heavier extensions such as local vectorisation of chat history.

The honest limits

SillyTavern stores chats and API keys as plain files on the server, so the instance should belong to one person or a trusted group. It does no inference itself; you need an API key or a model plan.

What people run SillyTavern for

Chat from any device

Same characters and history on phone, tablet and desktop.

Shared roleplay group

One instance for a small group with separate personas.

Remote front-end for a model plan

Point SillyTavern at a hosted KoboldCpp, Ollama or llama.cpp endpoint and keep sampler presets in one place.

Licence and version policy

ItemPosition
Upstream licenceAGPL-3.0
Sold as managed hostingYes
TenancySingle tenant — one customer per instance
PatchingCritical advisories within 24 hours, high severity within 72

Our full position on licences, including the applications we decline to sell, is on the licensing page.

Works well with SillyTavern

KoboldCpp logo

KoboldCpp

A single-binary GGUF server with its own UI and a KoboldAI API.

from $13.99/moDetails →Ollama logo

Ollama

Your private LLM server — pull a model, get an API, keep every token on your own box.

from $16.99/moDetails →llama.cpp logo

llama.cpp

The reference GGUF inference server, with nothing between it and the CPU.

from $13.99/moDetails →Text Generation WebUI logo

Text Generation WebUI

Oobabooga’s all-in-one interface for running and testing local models.

from $16.99/moDetails →

More AI assistants & chat we host

OpenClaw logo

OpenClaw

Your always-on personal AI assistant, running 24/7 on a server you control.

from $9.99/moDetails →Open WebUI logo

Open WebUI

A ChatGPT-style workspace for your team, pointed at any model you like.

from $5.99/moDetails →LibreChat logo

LibreChat

Multi-model chat with agents, plugins and conversation forking.

from $11.99/moDetails →LobeChat logo

LobeChat

A fast, polished chat UI with a large plugin and assistant marketplace.

from $11.99/moDetails →
Questions

SillyTavern hosting: your questions

Do I need a model plan too?
Only if you want local inference. SillyTavern happily drives a commercial API with your own key; pair it with an Ollama or KoboldCpp plan if you would rather keep everything in-house.
Can several people use one SillyTavern instance?
Yes. With enableUserAccounts switched on in config.yaml, each person gets their own handle, settings, extensions and data folder. Upstream is clear that account passwords give privacy between users rather than strong security, so share an instance only with people you trust.
How do I move my existing SillyTavern data across?
Your characters, chats, world info and settings live in the data folder, under one directory per user handle. Upload that folder over SFTP or use the Download Backup option in the account panel on your old install, and it drops into the new instance unchanged.
Which backends and APIs can it talk to?
Commercial chat APIs such as OpenAI, Claude and OpenRouter, plus local text-completion backends like KoboldCpp, llama.cpp, Ollama and text-generation-webui. You paste your own key or endpoint URL in the connection panel; nothing is routed through us.
Do third-party extensions and plugins work?
Yes. Extensions installed from the UI go into the third-party extensions folder and server plugins into plugins, both of which persist across restarts and updates. Extensions that download large local models will be limited by the plan’s RAM.

Run SillyTavern without running a server

A dedicated SillyTavern instance, deployed and maintained by us. Month to month, cancel whenever.

Browse the catalogue Talk to a human