a self-hosted webui for 30+ generative ai

Setup and run a local LLM and Chatbot using consumer grade hardware.

Gradio based tool to run opensource LLM models directly from Huggingface

Information on optimizing python libraries specifically for oobabooga to take advantage of Apple Silicon and Accelerate Framework.

An open source, Gradio-based chatbot app that combines the best of retrieval augmented generation and prompt engineering into an intelligent assistant for modern professionals.

Pre-built wheels for llama-cpp-python across platforms and CUDA versions

Local character AI chatbot with chroma vector store memory and some scripts to process documents for Chroma

GPU-accelerated LLaMA inference wrapper for legacy Vulkan-capable systems a Pythonic way to run AI with knowledge (Ilm) on fire (Vulkan).

Notolog Markdown Editor

Tool for test diferents large language models without code.

Experimental interface environment for open source LLM, designed to democratize the use of AI. Powered by llama-cpp, llama-cpp-python and Gradio.

This repository is a CUA (computer use agent) system that, using the Qwen3-VL model on Ubuntu computers, aims to perform tasks on your behalf using the keyboard and mouse in a local Sandbox environment in GGUF format, based on the commands you provide.

UnOfficial Gradio Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

A financial chatbot powered by an LLM and retrieval-augmented generation.

A quick and optimized solution to manage llama based gguf quantized models, download gguf files, retreive messege formatting, add more models from hf repos and more. It's super easy to use and comes prepacked with best preconfigured open source models: dolphin phi-2 2.7b, mistral 7b v0.2, mixtral 8x7b v0.1, solar 10.7b and zephyr 3b

Simple chat interface for local AI using llama-cpp-python and llama-cpp-agent

TAO71 I4.0 is an AI created by TAO71 in Python.

SOLAIRIA is a free tool with minimal dependencies that lets you interact with text-generation AI LLMs of your choice privately by running on your own local hardware offline.

A comprehensive toolkit for training and running lightweight adapters for GGUF-based language models (ERNIE, Llama, Mistral, Phi-3, etc.) without modifying the base model.

YouTube API implementation with Meta's Llama 2 to analyze comments and sentiments

Clippy resurrected as an AI front end. 📃📎👀

Genshin Impact Character Chat Models tuned by Lora on LLM

A Genshin Impact Question Answer Project supported by Qwen1.5-14B-Chat

Runpod-LLM provides ready-to-use container scripts for running large language models (LLMs) easily on RunPod.

This is a adaptive RAG system decoupled ready for deployment and production

Multimodal prompt generator nodes for ComfyUI, designed to generate prompts for QwenImageEdit and Wan2.2. Supports local LLM / local GGUF models (Qwen3-VL, Qwen2.5-VL) and Qwen API for image and video prompt generation and enhancement.

ProfessorConnected is an API-powered tool that helps you discover professors with similar research interests by analyzing their arXiv publications using advanced NLP and vector search techniques.

EPSILON OME TRAINER is a desktop application that is designed to serve as a tool to generate free, unlimited problems that are similiar to the Spanish Mathematical Olympiads' ones.

llama-cpp-python(llama.cpp)で実行するGGUF形式のLLM用の簡易Webインタフェースです。

Presage is an API-driven fortune-telling application that utilizes FastAPI and Large Language Models (LLMs) to analyze users’ palm images. By leveraging llm-cpp-server and Lang-Segment-Anything (SAM-Lang), it processes hand images to generate insightful analyses.