Ever dreamt of having your own AI stack that you can control, tweak, and build upon — without relying entirely on cloud APIs? That’s what I’ve done with my homelab. This post walks you through the components of my AI stack, how I use it across different tools, and hopefully inspires you to build your own.

🚀 Why I Built a Personal AI Stack#

In a world where most AI tools are cloud-locked and usage-limited, I wanted something private, flexible, and local — an AI assistant I could shape to my needs. Whether I’m brainstorming, coding, automating, or organizing my life — this stack powers it all.

🧩 Architecture Overview# 

---

config:

  layout: elk

  theme: mc

  look: neo

---

flowchart TD

 subgraph subGraph0["Core AI Stack"]

        Ollama["Ollama Local LLM Engine"]

        OpenWeb["OpenWeb-UI Chat Interface"]

        LiteLLM["LiteLLM API Manager (LLM request routing)"]

        SD["Stable Diffusion Image Generator"]

        n10["Postgres pgvector"]

  end

 subgraph subGraph1["Use cases"]

        Obsidian["Obsidian - Note-taking with AI"]

        VSCode["VS Code - AI Coding Assistant"]

        Nextcloud["Nextcloud Smart Office Tools"]

        HA["Home Assistant"]

        n8n["n8n - Automated Workflows"]

        Experiments["Learning - Testing AI Features"]

  end

 subgraph s1["Cloud LLMs"]

        OpenAI["OpenAI"]

        n9["Others"]

        Gemini["Gemini"]

  end

    Ollama <-- for local LLM ---> OpenWeb

    OpenWeb -- for Cloud LLM --> LiteLLM

    OpenWeb -- Image generation --> SD

    LiteLLM -- Multiple OpenAI keys --> OpenAI

    LiteLLM -- Multiple keys --> n9

    LiteLLM -- Multiple Gemini keys --> Gemini

    Obsidian --> LiteLLM

    VSCode --> LiteLLM

    Nextcloud --> LiteLLM

    HA --> LiteLLM

    n8n -- Cloud LLM --> LiteLLM

    n8n -- for RAG --> n10

    Experiments --> OpenWeb

    n10@{ shape: db}

    Obsidian@{ shape: card}

    VSCode@{ shape: card}

    Nextcloud@{ shape: card}

    HA@{ shape: card}

    n8n@{ shape: card}

    Experiments@{ shape: card}

    OpenAI@{ shape: procs}

    n9@{ shape: procs}

    Gemini@{ shape: procs}

    style Ollama fill:#C8E6C9

    style OpenWeb fill:#C8E6C9

    style LiteLLM fill:#C8E6C9

🛠️ Core Components Explained#

🧠 Ollama – Local LLM Runner#

Ollama acts as the engine to run Large Language Models (LLMs) locally on my hardware. It’s optimized, efficient, and supports multiple open-source models like LLaMA, Mistral, and more.

💬 OpenWeb-UI – The Friendly Face#

This is the user interface for chatting with LLMs. It connects to Ollama or routes through LiteLLM. I like it for its clean design, chat history, and plugin support.

🔑 LiteLLM – API Management & Routing#

This server is the smart API orchestrator. It allows:

  • Key & quota management

  • Routing requests between local (Ollama) and cloud providers (OpenAI, Gemini)

  • Load balancing between different models and endpoints

Perfect for managing API usage in a multi-service setup.

🎨 Stable Diffusion – AI Art Generator#

Using local models, I can generate stunning AI images without sending data to the cloud. It integrates well with OpenWeb-UI for seamless text-to-image tasks.

🧠 How I Use This Stack Daily#

✍️ Obsidian – Smart Note-Taking#

With AI-powered plugins, Obsidian connects to my stack to generate content, summaries, and brainstorm ideas. It’s like having a creative co-pilot for journaling and knowledge management.

💻 VS Code – Code with a Brain#

Using the Cline extension, my VSCode connects to the stack for code generation, debugging help, and explanations. It’s like ChatGPT, but self-hosted and customized for my workflows.

🗂️ Nextcloud – Office, but Smarter#

Think Google Docs or MS Office with AI — powered by my own backend. Summarizing documents, writing reports, or generating slides with AI help — all done privately.

🏠 Home Assistant – My Smart Home Butler#

By integrating with Home Assistant, I can interact with my home using natural language:

“Hey Jarvis, how’s the weather?”
“Turn off all the lights and summarize today’s news.”

🔄 n8n – Automated AI Workflows#

This no-code/low-code automation platform connects with my stack to run tasks like:

  • Auto-generating replies

  • Summarizing emails

  • Creating blog outlines from notes

🧪 Experiments#

My AI lab wouldn’t be complete without a test bench. I use my stack to prototype new AI use cases — like PDF summarizers, chatbots, or creative writing tools — quickly and without limits.

🧰 Hardware + Software Stack#

Component Details
GPU NVIDIA GTX 1660 Super
Host Linux container (LXC/Docker)
AI Support NVIDIA Docker + CUDA libraries
Models LLaMA, Mistral, OpenAI GPT, Gemini
Image Models Stable Diffusion, SDXL, DreamShaper

This setup balances power and affordability — and is more than enough for most personal LLM and image generation tasks.

🌟 Final Thoughts#

Building my own AI stack was one of the most empowering things I’ve done in recent years. It gave me:

  • Full control over AI tools

  • Endless ways to innovate

  • A privacy-first way to use generative AI

If you’re into homelabs, automation, or just want to explore AI beyond APIs — this setup is a great place to start. And you don’t need enterprise GPUs to get started — just a bit of curiosity and tinkering spirit.

💡 Inspired to Build Your Own?#

Feel free to copy this architecture, tweak it, or even ask me questions. Your personal AI assistant is just a homelab away.