Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models.

Clipboard Conqueror is a novel copy and paste copilot alternative designed to bring your very own LLM AI assistant to any text field.

Plugin that lets you ask questions about your documents including audio and video files.

Creates an index of images, queries a local LLM and adds tags to the image metadata

Like ChatGPT's voice conversations with an AI, but entirely offline/private/trade-secret-friendly, using local AI models such as LLama 2 and Whisper

Croco.Cpp is a 3rd party testground for KoboldCPP, a simple one-file way to run various GGML/GGUF models with KoboldAI's UI. (for Croco.Cpp, in Cuda mode mainly!)

A set of bash scripts to automate deployment of GGML/GGUF models [default: RWKV] with the use of KoboldCpp on Android - Termux

An AI Discord bot that connects to a koboldcpp instance by API calls. Have a more intelligent Clyde Bot of your own making!

Local LLM Discord Bot

Ditana Assistant: AI-powered CLI/GUI tool for intelligent assistance, leveraging LLMs with OS interaction capabilities and context augmentation, optionally via Wolfram|Alpha

XMPP Bot designed for E2EE AI language model interactions

koboldcpp REST API wrapper for C#

The Ultimate Local LLM Discord Bot!!!

Rin's Discord Bot (GitHub ALT)

Basic vector database plugin that works wth KoboldAI. Adds documents, images, and audio files.

BlackLite-Tools provides UserMods for KoboldAI Lite

Run Llama 3.1 directly

KetisBot is a powerful Discord AI chatbot using KoboldCpp for text generation, web browsing, and image creation. It features slash commands for easy interaction and allows admin customization.

🧠 A fully self-hosted, universal AI chat interface powered by local LLMs. Designed for both desktop and laptop use — supports CPU and GPU (CUDA) execution. Features real-time streaming responses, clean minimalist UI, and no external server dependencies. Ideal for building your own private, offline AI assistant.