A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.

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

Packaging Ollama for Fedora linux

Local ML voice chat using high-end models.

End-to-end scripting workflow to automatically generate show notes from audio/video transcripts with Whisper.cpp, Llama.cpp, yt-dlp, and Commander.js

Self-evaluating interview for AI coders

Create characters in Unity with LLMs!

React Native binding of llama.cpp

Node.js binding of Llama.cpp

Ollama Web UI is a simple yet powerful web-based interface for interacting with large language models. It offers chat history, voice commands, voice output, model download and management, conversation saving, terminal access, multi-model chat, and more—all in one streamlined platform.

PowerShell automation to rebuild llama.cpp for a Windows environment.

TinyAGI is a lightweight, modular, and extensible Python-based AGI framework designed to create and manage AI agents seamlessly. It supports various model backends like OpenAI, Llama.cpp, Ollama, AlpacaX, and Tabitha, along with dynamic plugin loading for enhanced flexibility.

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.

Local Generative AI

Simplify and accelerate AI-powered application development with structured interfaces to models and powerful prompt execution environments.

Training materials on how to deploy generative AI models locally on your laptop or workstation.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

A static web ui for llama.cpp server. The llama.cpp chat interface for everyone. base on chatbot-ui

My website

Python script-supervisor iteratively executes script-agent and modifies it via LLM that is instructed with description of supervisor functioning and final goal, then at each iteration gets retval, stdout, stderr of current agent, and is asked to reply with next agent verbatim. Optional jailbreak attempt. TUI. Unsafe.