Ollama

Hugging Face's production server for LLMs

Drop-in OpenAI-compatible API for local models

The C++ engine that made local LLMs practical

Run language models privately on your own computer

Open-source distributed computing for Python and ML at scale

Open-source evaluation framework for RAG pipelines

The AI pair programmer most developers actually use

Enterprise access to OpenAI models via Microsoft Azure

AI-first code editor, forked from VS Code