SillyTavern provides a frontend for people who use large language models extensively.

docs.sillytavern.app
SillyTavern homepage screenshot

About SillyTavern

SillyTavern is a locally installed interface for interacting with text generation LLMs, image generation engines, and TTS voice models. It provides controls for LLM prompts, character cards, and connections to different backends.

It is only an interface and requires a separate LLM backend for inference, such as AI Horde, an OpenAI-compatible API, KoboldAI, or Tabby. Persistent conversations require a character card, and installation requires a system that can run NodeJS 20 or higher.

Key features

  • Character cards that set LLM behavior for persistent conversations
  • Advanced text generation settings with community-made presets
  • World Info support to create lore or save tokens
  • Group chats where characters talk to user or each other
  • Built-in RAG support to reference documents in chats
  • Extensions for image generation, TTS, web search and translation
Best for: Experienced LLM users who want detailed control over prompts, characters, and backend choice.
Good for
  • Connects to many local and cloud LLM backends, including AI Horde for immediate chatting
  • Runs on any system that supports NodeJS 20 or higher
  • Released under the AGPL-3.0 license
Watch out for
  • Only an interface and needs a separate LLM backend for inference
  • Needs a character card to keep persistent conversations
  • Has a steep learning curve for prompt control

SillyTavern at a glance

Type
Online tool
Pricing
Not confirmed. Check the site
Platforms
Android, Linux, Web, Windows
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

SillyTavern alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Chatbots & Assistants

Well-known listings from the same topic.

All 238

SillyTavern FAQ

What do I need other than SillyTavern?
Access to an LLM backend for inference. AI Horde can be used for out-of-the-box chatting, and other supported options include OpenAI-compatible API, KoboldAI, and Tabby.
What are the installation requirements?
A system that can run NodeJS 20 or higher. For LLM inference on the local machine, a 3000-series NVIDIA graphics card with at least 6GB of VRAM is recommended.
What is the difference between the release and staging branches?
Release is the stable branch for most users and is typically updated once a month. Staging has the latest features but may break and is updated several times daily.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing