Use your locally running AI models to assist you in your web browsing

A generalized information-seeking agent system with Large Language Models (LLMs).

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Run MemGPT-AutoGEN-Local LLM Together

A nifty little library for working with Ollama in Elixir.

OpenLocalUI: Native desktop app for Windows, MacOS and Linux. Easily run Large Language Models locally, no complex setups required. Inspired by OpenWebUI's simplicity for LLM use.

MVP of an idea using multiple local LLM models to simulate and play D&D

Chat with your pdf using your local LLM, OLLAMA client.

A local chatbot for managing docs

Unofficial entropix impl for Gemma2 and Llama and Qwen2 and Mistral

The client for the Symmetry peer-to-peer inference network. Enabling users to connect with each other, share computational resources, and collect valuable machine learning data.

Humanlike AI Chat is a terminal-based LLM UI designed to study how to bypass AI text detection.

📚 NovelGenerator - AI-powered fiction book generator that uses Ollama's LLMs to create complete novels with coherent plot structures, developed characters and multiple writing styles.

Run gguf LLM models in Latest Version TextGen-webui

Alacritty + Fish + Zellij + Starship + Neovim + i3 + Supermaven + Ollama 🦙 = 🚀

This project is a multi-agent security framework that utilizes multiple LLM models to analyze and generate comprehensive security briefs.

A library that manages tools (functions) for Local LLMs

A german workshop where you learn how to build RAGs with Langchain

This started out as a POC for chatting over my documents, but has turned into a whole framework for using LLMs.