Show HN: Local AI server with persistent memory, RAG and plugins

Category: ai-ml

Tags: local-ai, rag, persistent-memory

Score: 6.5/10 (Innovation: 6, Technical: 7, Documentation: 7, Utility: 6)

Server Nexe is a local AI server that provides persistent memory, RAG (Retrieval-Augmented Generation), and a modular plugin system, all running offline for full privacy. It integrates multiple inference backends (MLX, llama.cpp, Ollama) and offers a desktop app for easy setup, making it a practical tool for developers wanting to own their AI infrastructure.

Target audience: backend devs, data engineers, devops

Repository: https://github.com/jgoy-labs/server-nexe · Python · NOASSERTION · 9 stars

View on Hacker News