All stories
250 stories found
Self-Hosting n8n on a $6 VPS: Full Setup, Backups Included
Docker compose file, HTTPS, backups, and the memory limit that stopped my instance dying every three days. Running cost: about six dollars a month.
Fine-Tuning a Small Model on a Laptop with LoRA: Start to Finish
I fine-tuned a 3B model on 800 support tickets using a 12GB GPU. Dataset format, hyperparameters that worked, and how I knew it had gone wrong.
Which GPU Should You Buy for Local AI in 2026? (I Tested Five Price Brackets)
VRAM is the only spec that decides what you can run. Here is what each budget tier actually gets you, with measured tokens per second and the models that fit.
MCP Servers, Explained by Someone Who Wired Five of Them Up
What the Model Context Protocol actually does, a working config you can copy, and the security mistake I nearly made on day one.
How to Run a Local LLM on 8GB of RAM (What Actually Works in 2026)
I tested seven small models on an 8GB laptop with no dedicated GPU. Three were genuinely usable, four were not. Here is the exact setup, the quantization that worked, and the errors I hit.
CUDA Out of Memory: 9 Fixes That Actually Worked on My GPU
The full error, what each number in it means, and nine fixes ordered by how likely they are to solve your problem — starting with the two that fix it 80% of the time.
How I Cut My OpenAI API Bill by 71% Without Changing the Product
Seven changes, ranked by how much money each one saved. Caching was the biggest. Model routing was second. Prompt trimming barely mattered.
Ollama vs LM Studio vs Jan: I Used All Three for a Month
Three local AI apps, one month, the same laptop. Which one you should install depends on whether you want a terminal, a GUI, or something your non-technical colleague can use.
I Built a Chatbot for My Own Documents in One Evening (Free, Local, No API Key)
A working RAG setup over a folder of PDFs using Ollama and Chroma. Full code, the two mistakes that made my answers wrong, and how I fixed retrieval quality.
كيف تبني وكيل ذكاء اصطناعي يعمل على جهازك بدون إنترنت (Ollama + MCP) — جرّبته 3 أسابيع (2026)
بنيت وكيل AI محلي يقرأ ملفاتي وينفّذ أوامر على جهازي بدون إرسال أي بيانات للسحابة. هذه الخطوات الحقيقية، الأخطاء التي واجهتني، والحل الدقيق لكل واحدة.
أفضل 7 حلول أتمتة بالذكاء الاصطناعي بدون اشتراك (اختبرتها بنفسي 2026)
اختبرت 14 أداة أتمتة بالذكاء الاصطناعي خلال 30 يوماً واحتفظت بـ 7 فقط تعمل مجاناً بدون اشتراك شهري. هذا الدليل يضم جدول مقارنة، أوامر تثبيت جاهزة للنسخ، والأخطاء التي واجهتها وحلولها.
كيف تؤتمت عملك بالذكاء الاصطناعي باستخدام n8n مجاناً (دليل عملي خطوة بخطوة 2026)
جرّبت أتمتة مهامي اليومية بـ n8n مع نماذج الذكاء الاصطناعي لمدة أسبوعين كاملين: وفّرت 11 ساعة عمل أسبوعياً بدون كتابة كود تقريباً. هذا هو الدليل الكامل بالخطوات والأوامر والأخطاء التي واجهتها.