SillyTavern provides a single unified interface for many LLM APIs (KoboldAI/CPP, Horde, NovelAI, Ooba, Tabby, OpenAI, OpenRouter, Claude, Mistral and more), a mobile-friendly layout, Visual Novel Mode, Automatic1111 & ComfyUI API image generation integration, TTS, WorldInfo (lorebooks), customizable UI, auto-translate, more prompt options than you'd ever want or need, and endless growth potential via third-party extensions.
SillyTavern (or ST for short) is a locally installed user interface that allows you to interact with text generation LLMs, image generation engines, and TTS voice models.
Beginning in February 2023 as a fork of TavernAI 1.2.8, SillyTavern now has over 100 contributors and 2 years of independent development under its belt, and continues to serve as a leading software for savvy AI hobbyists.
*`release` -🌟 **Recommended for most users.** This is the most stable and recommended branch, updated only when major releases are pushed. It's suitable for the majority of users. Typically updated once a month.
*`staging` - ⚠️ **Not recommended for casual use.** This branch has the latest features, but be cautious as it may break at any time. Only for power users and enthusiasts. Updates several times daily.
If you're not familiar with using the git CLI or don't understand what a branch is, don't worry! The release branch is always the preferable option for you.
Since SillyTavern is only an interface, you will need access to an LLM backend to provide inference. You can use AI Horde for instant out-of-the-box chatting. Aside from that, we support many other local and cloud-based LLM backends: OpenAI-compatible API, KoboldAI, Tabby, and many more. You can read more about our supported APIs in [the FAQ](https://docs.sillytavern.app/usage/api-connections/).
The hardware requirements are minimal: it will run on anything that can run NodeJS 18 or higher. If you intend to do LLM inference on your local machine, we recommend a 3000-series NVIDIA graphics card with at least 6GB of VRAM. Check your backend's documentation for more details.
### Suggested Backends (not affiliated)
* [AI Horde](https://aihorde.net/) - use models hosted by volunteers. Requires no further setup
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - a community's favorite for running GGUF models locally
* [tabbyAPI](https://github.com/theroyallab/tabbyAPI) - a popular, lightweight, locally-hosted exl2 inference API
* [OpenRouter](https://openrouter.ai) - a single API for many cloud providers (OpenAI, Claude, Meta Llama, etc.) as well as popular community models.
SillyTavern is built around the concept of "character cards". A character card is a collection of prompts that set the behavior of the LLM and is required to have persistent conversations in SillyTavern. They function similarly to ChatGPT's GPTs or Poe's bots. The content of a character card can be anything: an abstract scenario, an assistant tailored for a specific task, a famous personality or a fictional character.
The name field is the only required character card input. To start a neutral conversation with the language model, create a new card simply called "Assistant" and leave the rest of the boxes blank. For a more themed chat, you can provide the language model with various background details, behavior and writing patterns, and a scenario to jump start the chat.
To have a quick conversation without selecting a character card or to just test the LLM connection, simply type your prompt input into the input bar on the Welcome Screen after opening SillyTavern. Please note that such chats are temporary and will not be saved.
To get a general idea on how to define character cards, see the default character (Seraphina) or download selected community-made cards from the "Download Extensions & Assets" menu.
(This allows git usage **only** in GitHub Desktop, if you want to use `git` on the command line too, you also need to install [Git for Windows](https://gitforwindows.org/))
3. After installing GitHub Desktop, click on `Clone a repository from the internet....` (Note: You **do NOT need** to create a GitHub account for this step)
4. On the menu, click the URL tab, enter this URL `https://github.com/SillyTavern/SillyTavern`, and click Clone. You can change the Local path to change where SillyTavern is going to be downloaded.
6. To open SillyTavern, use Windows Explorer to browse into the folder where you cloned the repository. By default, the repository will be cloned here: `C:\Users\[Your Windows Username]\Documents\GitHub\SillyTavern`
7. Double-click on the `start.bat` file. (Note: the `.bat` part of the file name might be hidden by your OS, in that case, it will look like a file called "`Start`". This is what you double-click to run SillyTavern)
8. After double-clicking, a large black command console window should open and SillyTavern will begin to install what it needs to operate.
9. After the installation process, if everything is working, the command console window should look like this and a SillyTavern tab should be open in your browser:
10. Connect to any of the [supported APIs](https://docs.sillytavern.app/usage/api-connections/) and start chatting!
SillyTavern Launcher is an installation wizard that will help you get setup with many options, including installing a backend for local inference.
### For Windows users
1. On your keyboard: press **`WINDOWS + R`** to open Run dialog box. Then, run the following command to install git:
```shell
cmd /c winget install -e --id Git.Git
```
2. On your keyboard: press **`WINDOWS + E`** to open File Explorer, then navigate to the folder where you want to install the launcher. Once in the desired folder, type `cmd` into the address bar and press enter. Then, run the following command:
```shell
git clone https://github.com/SillyTavern/SillyTavern-Launcher.git && cd SillyTavern-Launcher && start installer.bat
These instructions assume you have installed Docker, are able to access your command line for the installation of containers, and familiar with their general operation.
We have a comprehensive guide on using SillyTavern in Docker [here](http://docs.sillytavern.app/installation/docker/) which covers installations on Windows, macOS and Linux! Give it a read if you wish to build the image yourself.
You will need two mandatory directory mappings and a port mapping to allow SillyTavern to function. In the command, replace your selections in the following places:
* [PublicPort] - The port to expose the traffic on. This is mandatory, as you will be accessing the instance from outside of its virtual machine container. DO NOT expose this to the internet without implementing a separate service for security.
* [DockerNet] - The docker network that the container should be created with a connection to. If you don't know what it is, see the [official Docker documentation](https://docs.docker.com/reference/cli/docker/network/).
* [version] - On the right-hand side of this GitHub page, you'll see "Packages". Select the "sillytavern" package and you'll see the image versions. The image tag "latest" will keep you up-to-date with the current release. You can also utilize "staging" and "release" tags that point to the nightly images of the respective branches, but this may not be appropriate, if you are utilizing extensions that could be broken, and may need time to update.
**Unsupported platform: android arm LEtime-web.** 32-bit Android requires an external dependency that can't be installed with npm. Use the following command to install it: `pkg install esbuild`. Then run the usual installation steps.
Most often this is for people who want to use SillyTavern on their mobile phones while their PC runs the ST server on the same Wi-Fi network. However, it can be used to allow remote connections from anywhere as well.
You may also want to configure SillyTavern user profiles with (optional) password protection: [Users](https://docs.sillytavern.app/installation/st-1.12.0-migration-guide/#users).
