SillyTavern MultiPlayer (STMP)

SillyTavern MultiPlayer is an LLM chat interface that allows multiple users to chat together with one or more AI characters. It also includes a sidebar chat for users only, and many tools for the Host to control the behavior of the AI and to moderate users.

Created by RossAscends

Support and Donations

If this software brings you and your friend's joy, donations to Ross can be made via:

| Ko-fi | Patreon | |-------|---------| | | |

For tech support or to contact RossAscends directly, join the SillyTavern Discord.

Installation

Typical

Make sure Node JS is installed on your system and has access through your firewall.
Clone this github repo into a new folder NOT the main SillyTavern folder. (git clone https://github.com/RossAscends/STMP/ in a command line, or use a Github GUI like Github Desktop)
Run STMP.bat to install the required Node modules and start the server.
On the first run, the server will create an empty secrets.json and a default config.json, as well as the /api-presets/ and /chats/ folders.
Open http://localhost:8181/ in your web browser.

Docker

STMP can also be installed via Docker, thanks to city-unit.
The Docker file can be found in /utils/

(instructions coming soon)

Using Horde

You can use Horde as an anonymous user, but that generally leads to slower response times.

To use your Horde API key in STMP, add it to secrets.json like this (server should run at least once):

{
    // some content
    "horde_key": "YourKeyHere",
    // some other content
}

Don't have one? Registering a HordeAI account is free and easy.

Multiuser Setup

This must be done AFTER completing all installation steps above.

Make sure your STMP server is running.
Run Remote-Link.cmd to download cloudflared.exe (only one time, 57MB).
the Cloudflared server will auto-start and generate a random tunnel URL for your STMP server.
Copy the URL displayed in the middle of the large box in the center of the console window.
DO NOT CLOSE THE CLOUDFLARE CONSOLE WINDOW
Share the generated cloudflared URL with the guest users.
User will be able to directly and securely connect to your PC by opening the URL in their browser.

Play

Chatting

User can change their display name at any time using either of the inputs at the top of the respective chat displays.
- You can have a different name for the User Chat and AI Chat.
- Usernames are stored in browser localStorage.
Chatting can be done in either chat windows by typing into the appropriate box and then either pressing the Send button (✏️), or pressing Enter.
Shift+Enter can be used to add newlines to the input.
Markdown formatting is respected.
Some limited HTML styling is also possible inside user messages.
Users with the Host role can hover over any chat message in either chats to see editing and deletion buttons.

The host will see the following controls:

Control Panel (🎛️)

AI Controls

AI Config Section

Mode can be clicked to switch between TC/CC mode, and HordeAI mode.
- 📑 = Completions
- 🧟 = Horde
Context defines how long your API prompt should be. Longer = more chat history sent, but slower processing times.
Response defines how many tokens long the AI response can be.
Streaming togles streamed responses on or off.
AutoAI Toggle to determine whether the AI should respond to every user input, or only on command from the Host.
Instruct sets the type of instruct sequences to use when crafting the API prompt.
Sampler sets the hyperparameter preset, which affects the response style.
API selector to choose which LLM API to use, and an Edit button to change its configuration.
Models allows selection of models served by the connected API.

Insertions Section

System Prompt defines what will be placed at the very top of the prompt.
Author Note(D4) defines what will be inserted as a system message at Depth 4 in the prompt.
Final Instruction(D1, "JB") defines what to send as a system message at Depth 1 in the prompt.

Adding/Editing APIs

Currently STMP supports Text Completions (TC), Chat Completions (CC), and HordeAI.

STMP has been tested with the following APIs:

TabbyAPI

YALS

KoboldCPP

Aphrodite

Oobabooga Textgeneration Webui (OpenAI compatible mode)

OpenRouter is supported in CC mode.

OpenAI official API

Anthropic's Claude

Other LLM backends that provide an Open AI compatible API should wotk with STMP.

Select Add new API from the API selector to open the API Editing panel.
A new panel will be displayed with new inputs: a. Name - the label you want to remember the API as b. Endpoint URL - this is the base server URL for the LLM API. If the usual URL does not work, try adding v1/ to the end. c. Key - If your API requires a key, put it in here. API Keys are saved in config.json. Do not share this file! d. Endpoint Type - select from Text Completions or Chat Completions as appropriate for the API endpoint. e. Claude - select this if the API is based on Anthropic's Claude model, because it needs special prompt formatting. f. Close - will cancel the API editing/creating process and return you to the main AI Config panel. g. Test - sends a simple test message to the API to get a response. This may not work on all APIs. h. Save - confirms the API addition/edit and saves it to the database. i. Delete - removes the APi from the database.
When all of the fields are filled out, press Save to return to the main Control panel display.

Prompt Insertions

System Prompt: Inserted into the top-level system prompt.
D4 "Author's Note": inserted above the 4 most-recent pre-existing chat history messages.
- Optional checkbox to insert the Description of the next-responding character here as well.
D1 "Jailbreak": inserted above the most recent pre-existing chat history message.
D0 "Post-history Instructions": inserted after all pre-existing chat history messages.
Response Prefill: Prefixes the upcoming AI response.

Adding Instruct/Sampler Presets

If you want to add more presets for Instruct formats or hyperparameter Samplers, put the JSON file into the appropriate folder:
Samplers go in /public/api-presets/
Instruct formats go in/public/instructFormats/
It's strongly recommended to look at the structure of STMP's default preset files.
SillyTavern preset files will not work.

Chats, Characters, and Crowd Controls (📜)

Past Chats

A list of past AI Chats, click one to load it.
Information listed with each past session item:
- AI characters in the chat history
- Number of messages in AI Chat
- Timestamp for the last message
The list is ordered in reverse chronological (newest chats first)

Managing Characters

Place any SillyTavern compatible character card into the /characters/ folder and restart the server.
Drag-drop a v2 card spec character card over the chat to import.
Characters can be added, removed, edited, or swapped out inside the 📜 panel.
Changing the character roster does not require restting the chat.

Editing Characters

Hosts will see a (🧠) next to Character Selectors. This will open a popup with the character definitions.
STMP handles three types of character definitions:
- Name - What is displayed as the character's name in the chat.
- Description - What goes into the prompt at either the top, or at D4 if 'D4 Char Defs' box is checked.
- First Message - What gets auto-inserted into a new chat with that character.
Embedded Lorebook - is currently not used by STMP, but is visible for user reference.
(👁️) at the top of the character definition panel will show Legacy Fields
- Legacy Fields are read-only. STMP does not use them.
- Legacy fields = Personality, Example Messages, and Scenario.
Save will update the character definitions.
Close will close the popup with no changes.

Why are Personality, Scenario, and Example Messages considered 'Legacy'?

Personality and Scenario are outdated distinctions without a meaningful purpose, and should be incorporated into the Description.
Example Message can also be incorporated into the Description. We recommend doing so in the form of AliChat.

Crowd Controls

(🎨) (all users) Three inputs for Hue, Saturation, and Lightness to define the base color for STMP UI theming.
(🎶) (all users) is a toggle that will play/stop a looping b

STMP

Install / Use

README