Înapoi la articole →

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 20
  1. Disclaimer, this blog post is a proof of concept and not a security proposal.

  2. Authelia as an OAuth2 OpenID Connect provider

    In my previous post I used Authelia in front of a self-hosted service to handle authentication before users are allowed.

  3. I like running a few services either on my private homelab or on various cloud VPS.

  4. How to proxy IMAP traffic using Dovecot and Docker

    I am in the process of migrating my self-hosted email server to a new virtual private server.

  5. AI Coding Agents with One Shared Memory

    coding agents are useful, but they forget.

  6. run Linux containers on your macbook with Apple container

    Containers is an package application with all the files, libraries, and runtime it needs.

  7. Yeelight Wireless Smart Dimmer in Home Assistant

    I spent some time trying to connect a Yeelight Wireless Smart Dimmer to Home Assistant.

  8. Build your own ChatGPT-like for free

    I want a simple way to experiment with LLMs from my (very old) archlinux machine that has no GPU.

  9. I want to run Ubuntu Virtual Machines on my Macbook

    I use multiple computers and multiple mobile devices.

  10. Protecting Your sites with Traefik's Fail2ban Plugin

    I was looking at my logs and analytics, and I saw something interesting.

  11. Getting Started with OpenCode and LM Studio

    Run OpenCode, an AI coding agent on your own machine — no cloud, no API, no data ever leaving your computer privacy first and no costs!

  12. I Replaced Every Notification Service With Apprise

    I can use apprise in Home Assistant and in my scripts and got signal, slack, email and many more working perfectly!

  13. LiteLLM as a Local Model AI Gateway

    LiteLLM AI Gateway (LLM Proxy) This project shows a simple pattern: run multiple local model servers, place LiteLLM in front of them, and expose one OpenAI-compatible endpoint for apps to use.

  14. How to Connect Claude Code to Osaurus MCP

    If you want to use Claude Code together with Osaurus, there are two different pieces to understand: Model backend — the LLM that answers your prompts MCP tools — the tools Claude Code can call This is the most important idea: Osaurus MCP gives Claude Code…

  15. Use Brave Leo with a Local LLM for Maximum Privacy

    Brave’s built-in privacy-first AI assistant, Leo, supports connecting to a local OpenAI-compatible server.

  16. Running vLLM-MLX on Apple Silicon

    Want to run modern LLMs locally — with an OpenAI-compatible API, multimodal support, and strong performance on Apple Silicon?

  17. If you’re running a home lab and tired of manually provisioning VMs, I’ve got something for you.

  18. Docker Contexts: Managing Multiple Docker Environments

    Introduction If you work with Docker long enough, you stop having one Docker environment.

  19. Prologue – Why do this at all?

  20. 🎉 If you want a self‑contained, production‑ready reverse proxy that automatically provisions TLS certificates from Let’s Encrypt and uses LuaDNS as the DNS provider, you’re in the right place.