kobold_assistant VS SillyTavern

My project, https://github.com/lee-b/kobold_assistant, is similar to this: currently works locally, listens and responds in a loop, but doesn't function (well) remotely through a server or anything. There is a mumble branch that works over a mumble voice chat, but it has echo/feedback/noise reduction problems right now.

KoboldAI has text completion and text chat interface built in, and I built (or am building) https://github.com/lee-b/kobold_assistant to provide a voice chat interface to that, and I have an 'ai' command that I can run from a linux shell, for any time I want the same AI to assist with anything in a command pipeline, and some steam games already use it. LocalAI will provide a local adapter to make OpenAI-based stuff use a local model instead -- I don't think this talks to KoboldAI, but I plan to modify it to do so, if it doesn't already. Finally, I plan to run (or build) something similar to SillyTavern, but instead of "joke"/fun anime characters, make it like an advisory council, where there's a philosophy advisor, a scientific advisor, an economics advisor, and so on all in a chat room, and I can just post ideas or articles I'm interested in, to get feedback from multiple perspectives, all driven by one AI -- or maybe a small number of AIs, like a specialised medical model or science or law model, and then a general model for everything else.

kobold-assistant uses whisper. https://github.com/lee-b/kobold_assistant

Right, but it's certainly easier for people who might not even know what "API" stands for, and that's quite nifty. As far as self-hosted frontends go, I can personally recommend SillyTavern[1] in the browser, ChatterUI[2] on mobile, and ShellGPT[3] for CLI. LobeChat looks pretty cool, though! I'll definitely check it out.

[1] https://github.com/SillyTavern/SillyTavern

[2] https://github.com/Vali-98/ChatterUI

[3] https://github.com/TheR1D/shell_gpt

I don't think there is any enumeration for {{char}} macros. Here is some good discussion on the subject.

As for SillyTavern, you need the main SillyTavern frontend and SillyTavern-extras (for TTS, STT, etc.) They're pretty easy to install. SillyTavern connects to oobabooga and SillyTavern-extras via API.

Finally, no matter what backend I use, I need it to be compatible with my power-user frontend, SillyTavern. That way I always use the same UI, with the characters I created and extensions I want, e. g. web search, XTTS text-to-speech and Whisper speech recognition for real-time voice chat - and all of that local!

SillyTavern v1.10.5 frontend (not the latest as I don't want to upgrade mid-test)