Skip to content

Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)

Notifications You must be signed in to change notification settings

derekcoleman/TavernAI

This branch is 122 commits behind TavernAI/TavernAI:main.

Folders and files

NameName
Last commit message
Last commit date
Nov 24, 2023
Nov 30, 2023
Oct 3, 2023
May 5, 2023
Jan 25, 2023
Apr 16, 2023
Jan 25, 2023
May 2, 2023
Apr 16, 2023
May 19, 2023
Nov 27, 2023
Nov 27, 2023
Nov 9, 2023
Nov 27, 2023
Mar 4, 2023

Repository files navigation

TavernAI

TavernAI is an atmospheric frontend for chat and storywriting, compatible with many backends!

Screenshots:

Download:
Run online:
Links:

Features

  • Character creation
  • Online character database
  • Group chat with multiple characters at the same time
  • Story mode
  • World info
  • Message swiping
  • Configurable generation settings
  • Configurable interface themes, including one that resembles CharacterAI
  • Configurable backgrounds, including beautiful defaults to select from
  • Edit, delete, and move any message
  • GPT-4.5 picture recognition

How to install

  1. Download and install: Node.js
  2. Download TavernAI

Then:

  • On Windows: Start TavernAI by running Start.bat
  • On Linux: Start TavernAI by running start-linux.sh
  • On other OSes: Run npm install to install dependencies, then run node server.js to start the server

For detailed instructions on how to setup TavernAI with KoboldAI or NovelAI:

Supported Backends

Tips

Use this button to edit the message:

If the message is not finished, you can simply send the request again, or say "continue", depending on the model. It should understand that you want to continue the message.

Additional materials

Contact

Humi (the original developer):

  • Discord: Humi#5044


About

Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • JavaScript 75.4%
  • HTML 11.8%
  • CSS 11.3%
  • Jupyter Notebook 1.4%
  • Shell 0.1%
  • Dockerfile 0.0%