simple-proxy-for-tavern VS Nuggt

Been using 1.9 for a while now, but heard about all the nice new extras in 1.1 so I decided to upgrade today. Silly me! Well ST Itself is running fine I've got that up no issues, extras is installed and koboldcpp is up to date...but it won't connect ST to KCPP. That being https://github.com/anon998/simple-proxy-for-tavern. It's worked like a dream for weeks up until today when I went to update and now the two can't talk. I did a fresh git pull of a new version - nothing. Rolled back to 1.9.7 - and it works like a charm. Anyone else had these issues?

https://github.com/anon998/simple-proxy-for-tavern/issues/25 It threw this error at me for a moment when I tried open AI, but not when running my Local LLM Via Kobold.

Still, nothing beats the SillyTavern + simple-proxy-for-tavern setup for me. But currently there's even a known issue with that and koboldcpp regarding sampler order used in the proxy presets (PR for fix is waiting to be merged, until it's merged, manually changing the presets may be required).

I’m using this https://github.com/anon998/simple-proxy-for-tavern

SillyTavern is just a frontend so it's as fast or slow as your backend. With simple-proxy-for-tavern you can use llama.cpp directly, no Python involved, so SillyTavern will be as fast as llama.cpp itself.

I also use the simple-proxy-for-tavern in between koboldcpp and the frontend, which does some magic behind the scenes to improve things further. Takes some time to understand and configure it all, but once done, it's definitely worth the effort, as nothing beats that setup for roleplaying and chat.

Really? Then we definitely have different experiences (or different ways to interact) with Guanaco. It's been the most unrestricted model I've tried, and I tried them all, but I'm using SillyTavern and the simple-proxy-for-tavern which combined with a little prompting liberates basically any model.

Why reinvent the wheel? Just use SillyTavern, ideally with the simple-proxy-for-tavern. That does it all, and more.

Yes, there is a lot of potential. You can check this project for agents: https://github.com/Nuggt-dev/Nuggt/ . Currently I only have "simple" projects: mostly 0-shots LLMs to get some responses. Agents are not yet mature enough to be integrated in production environments.

Check out the Github Repository

Things are changing every day. Take a look here: https://github.com/Nuggt-dev/Nuggt This is AutoGPT equivalent using a self hosted model. See what it can do.

Automate any task with a single AI Command (https://github.com/Nuggt-dev/Nuggt)

Demo Video: https://github-production-user-asset-6210df.s3.amazonaws.com/52075633/244840595-00e7c82c-61fe-4f04-b589-d65b97f441ff.mp4 🔎 Call for Feedback: We invite the community to try out Nuggt and provide valuable feedback. Let us know your thoughts, suggestions, and any improvements you'd like to see. Your feedback will help us shape the future of Nuggt and make it even better. 🔗 Find Nuggt on GitHub (We are looking for collaborators): https://github.com/Nuggt-dev/Nuggt 🌟 Join the Nuggt Discord Server: https://discord.gg/gzdCDM84 💡 Follow our 30 Days 30 Tasks with Nuggt challenge on Twitter: https://twitter.com/OfficialNuggt PS: While our current implementation leverages the power of GPT-3.5, we recognise the need for cost-effective solutions without compromising functionality. Our ongoing efforts involve exploring and harnessing the potential of smaller models like Vicuna 13B, ensuring that task automation remains accessible to a wider audience.

🔗 Find Nuggt on GitHub (We are looking for collaborators): https://github.com/Nuggt-dev/Nuggt

🌟 Join the Nuggt Community: Get involved, contribute, and join the discussions on our GitHub repository. We're building a vibrant community, and we'd love to have you on board!