DevCodeLight 
Tiempo de lectura: 2 minutosMCP (Model Context Protocol) is an open standard, created by Anthropic, that defines how an AI assistant connects to external tools and data. It is the common way to say to a model: «here are these functions you can use». The MCPs are defined in the opencode.json file, under the key mcp. You have two … Read more
Tiempo de lectura: 4 minutosIf you have Twenty CRM installed on your own server, you can connect a Google account via OAuth so that Twenty can access Gmail. In this tutorial, we will: Google Cloud → OAuth → Twenty → Gmail Yes. Here’s a tutorial designed for Twenty Self-hosted CRM with Docker, to connect a Gmail account and allow … Read more
Tiempo de lectura: 2 minutosIf you have a landing, portfolio, or any static website (HTML/CSS/JS without backend) and want to host it for free with your own domain, GitHub Pages + Cloudflare is one of the fastest combinations to set up. In this tutorial, I will mount the real case I used for the Convivia landing page, but the … Read more
Tiempo de lectura: 2 minutosI’ve been following the releases of open models for days, and the one from August 26th, 2026 is worth paying attention to even if you don’t live on X/Twitter AI. Alibaba has launched Qwen3.8-Flash-Next: a Mixture-of-Experts model with 125 billion parameters in the backbone, but only 6 billion active per token. Add to that an … Read more
Tiempo de lectura: 2 minutosOracle has started sending a notice to users of the Always Free plan indicating that free resources on instances Ampere A1 are being reduced. If you do not take action before the indicated date, Oracle will automatically terminate the instances that exceed the new limit. Oracle is sending a similar email to this: Beginning on … Read more
Tiempo de lectura: < 1 minutoStep-by-step guide based on the real installation of KAT-Coder-V2.5-Dev-APEX-MTP in ollama Before installing anything: evaluate if the model is worth it (https://huggingface.co/gbuzhf/KAT-Coder-V2.5-Dev-APEX-MTP-GGUF) Not all Hugging Face (HF) repos are created equal. Before downloading several GB, it’s worth checking: Good sign Alarm sign Author recognized in the community (bartowski, unsloth, etc.) or base model with a … Read more
Tiempo de lectura: 2 minutosToday we are going to implement PUSH notifications in Android/iOS for React Native using the Expo Notifications library. First, we will install the required libraries: npm install expo-install-expo-notifications expo-install-expo-device expo-install-expo-constants Once installed we will use this code which also generates two types of tokens: import { Notifications } from ‘expo-notifications’; import { Device } from … Read more
Tiempo de lectura: 2 minutosOllama does not support native tags from some Hugging Face repositories (such as I-Compact, Balanced, etc.) when they do not conform to their standard quantization schema (Q4_K_M, Q5_K_S…). The solution is to manually download the .gguf and register it with a Modelfile. Repo: https://huggingface.co/mudler/Qwen3.6-35B-A3B-APEX-GGUF For a 16GB RTX 5060 Ti, the suitable variant is I-Compact … Read more
Tiempo de lectura: < 1 minutoToday we are going to increase the response time allowed in an AI local model on Ollama that functions below the security perimeter using a Nginx Proxy Manager. To do this, we are going to Nginx Proxy Manager. We open Proxy Hosts > We open our host > Select Edit and we go to Advanced. … Read more
Tiempo de lectura: < 1 minutoThis tutorial is for when your physical disk is large (e.g. 1 TB), but the operating system only recognizes a part (e.g. 100 GB) due to the default LVM configuration in Ubuntu. To ensure that your system uses LVM and confirm where the free space is, run: Bash lsblk Your goal is to identify the … Read more
