# Server-nexe: Local AI server with RAG memory, multi-backend inference, and plugins

**URL:** <https://discuss.huggingface.co/t/server-nexe-local-ai-server-with-rag-memory-multi-backend-inference-and-plugins/175348>\
**Category:** Show and Tell\
**Created:** [April 17, 2026, 6:29pm UTC](https://discuss.huggingface.co/t/server-nexe-local-ai-server-with-rag-memory-multi-backend-inference-and-plugins/175348 "2026-04-17T18:29:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![JGoy](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jgoy/32/59596_2.png) [@JGoy](https://discuss.huggingface.co/u/JGoy)\
**Post date:** [April 17, 2026, 6:29pm UTC](https://discuss.huggingface.co/t/server-nexe-local-ai-server-with-rag-memory-multi-backend-inference-and-plugins/175348/1 "2026-04-17T18:29:33Z")

</div>

Hi everyone! I’d like to share **server-nexe** , an open-source, fully local AI server I’ve been building.

**What it does** server-nexe is a FastAPI server that runs 100% on your machine. No cloud, no telemetry. It combines LLM inference with persistent RAG memory seamlessly.

**Key features**

- **Multi-backend inference:** Switch backends with a single config parameter!

- **Persistent RAG memory:** Uses Qdrant + 768-dim embeddings across 3 specialized collections. The AI actually _remembers_ context between sessions.

- **Automatic Plugin System:** Easily extendable.

- **OpenAI-compatible API:** Acts as a drop-in replacement for your existing apps.

- **macOS Installer (DMG with wizard):** Automatically detects your hardware and recommends the best backend and models based on your RAM.

🎉 **v1.0.0-beta is out!** This is the first public MVP, and I am very open to community feedback.

**Why I built it** I wanted an AI server that actually remembered things across sessions. One question led to another, and my “learning by doing” approach got a bit out of hand! I’m not trying to compete with cloud services; I want to provide infrastructure for those who want to truly own their AI stack.

Documentation: 39 docs across 3 languages (CA/EN/ES) — structured to be read by both humans and AIs

Built in Barcelona · Apache 2.0 · Feedback highly welcomed!

**Links**

- **GitHub:** [https://github.com/jgoy-labs/server-nexe](https://github.com/jgoy-labs/server-nexe)

- **Docs:** [https://server-nexe.org](https://server-nexe.org/)

 ![Ligth](https://us1.discourse-cdn.com/hellohellohello/original/3X/8/8/8801cee384f76243dfa93988c501cbe37514bd17.png)