deepseek

Anything Llm

JavaScript

AnythingLLM is a full-stack RAG application that turns documents into intelligent chatbots. Run local LLMs via Ollama or LM Studio for complete data privacy.

Vllm

Python

vLLM is a high-throughput LLM serving engine using PagedAttention to optimize GPU memory. Deploy Llama and DeepSeek models via an OpenAI-compatible API today.

Ollama

Go

Ollama is an open-source tool for running LLMs locally on macOS, Linux, and Windows. Deploy Llama 3 and Gemma 3 with GPU acceleration via a simple REST API.