AI & self-hosting tutorials
AI and self-hosting: local models with Ollama, a chat interface, when you need a GPU, image generation, transcription, vector databases, RAG and automation.
How to use OpenHands as an AI software engineer
OpenHands takes a task and writes, runs and debugs the code on its own. Here is how to use it safely.
Updated 7/20/2026AI & self-hostingHow to build a customer chatbot with Dify
Use Dify to create an assistant that answers from your company documents, without writing code.
Updated 7/20/2026AI & self-hostingHow to extract web data without code, using Maxun
Build robots that collect data from websites by clicking, without writing a line of code.
Updated 7/20/2026AI & self-hostingHow to run your own self-hosted AI coding assistant
A coding assistant like Copilot, but on your server, with local models and no monthly subscription.
Updated 7/20/2026AI & self-hostingHow to automate with AI using n8n
Connect AI models to your apps in visual automated flows with n8n, no code.
Updated 7/20/2026AI & self-hostingHow to run an OpenAI-compatible API on your server
Replace the OpenAI API with a compatible local one, so your apps use your own models.
Updated 7/20/2026AI & self-hostingHow to choose an AI model for your hardware
How many parameters, how much memory: here is how to match the AI model to your server resources.
Updated 7/20/2026AI & self-hostingHow to set up a vector database for AI
Vector databases store the meaning of text, essential for semantic search and chatbots over your documents.
Updated 7/20/2026AI & self-hostingHow to build a chatbot on your documents (RAG)
Combine a local model with your documents so it answers questions based on them, using the RAG technique.
Updated 7/20/2026AI & self-hostingHow to generate images with Stable Diffusion on your server
Run your own AI image generator with Stable Diffusion, private and unlimited.
Updated 7/20/2026AI & self-hostingHow to transcribe audio to text with Whisper
Turn audio recordings into text with Whisper, the open-source transcription model, on your server.
Updated 7/20/2026AI & self-hostingHow to run local LLMs with Ollama
Run language models directly on your server with Ollama, private and with no per-token costs.
Updated 7/20/2026