llama-benchy: llama-bench-style LLM benchmarks for any OpenAI-compatible endpoint
If, like me, you run your models locally and sovereignly, you know the problem: I want to know how...
Read More
Category: News
Firecrawl in Your Own LAN: Sovereign Web Scraping with a Local Ollama Server
It has been itching me for quite a while: Firecrawl self-hosted, in my own LAN, with no cloud...
Read More
Sovereign AI on a 10-year-old office PC: NemoClaw on a Dell OptiPlex 5040 with my own Ollama server
Why NemoClaw is moving into my AI workshop Over the past few weeks I’ve shown you in several...
Read More
Sovereign AI in the Home Network: Running the Hermes Agent Dashboard Securely as a systemd Service
My Hermes Agent has been running productively on my application server for several weeks: as a...
Read More
An MCP Server for Multi-GPU Monitoring – Step by Step with Python, pynvml and EMA Smoothing
In my last posts I built the inference layer (Ollama, TensorRT-LLM) and the orchestrator layer...
Read More
NeMo Agent Toolkit – Multi-Agent Supervisor-Pattern local
After my last post, where I dissected the ReAct loop in detail and built the first custom GPU...
Read More
Adding a new board to ESP-Claw: Board adaptation for the Guition JC1060P470
After I showed you in Part 2 of my ESP-Claw series how I compiled ESP-Claw for the first time,...
Read More
ESP-IDF v5.5.4 einrichten und ESP-Claw bauen – Schritt für Schritt
After I introduced the vision in Part 1 of my ESP-Claw series – bringing a local AI agent to life...
Read More
Sovereign AI on a Microcontroller: Bringing an AI Agent to Life on HMI Hardware with ESP32-Claw – Series Kickoff
After I showed you in my post on “Sovereign AI” how I built my own independent LLM...
Read More
Your Personal AI Stylist: How to Build the Style Checker with Qwen3-VL & Ollama!
Your Style Dilemma: You stand in front of your closet in the morning, the clock is ticking, and...
Read More
Automating Enchanted Children’s Stories with AI & n8n
Imagine receiving a beautifully crafted children’s story by email—complete with vivid...
Read More
How to Install and Use OpenAI’s Whisper Locally for Automatic Transcription and Translation
Imagine having an effortless way to convert your favorite podcasts, YouTube videos, or conference...
Read More
- Hermes Agent as a Native Desktop App on Windows
Nous Research has given its open-source Hermes Agent something with the “Surface Release” (version 0.16.0, June 2026) that I had been waiting for a long time: a true native desktop app for macOS, Linux, and Windows. Until now, Hermes Agent was a command-line and gateway tool. But with the new release, there is now a… Read more: Hermes Agent as a Native Desktop App on Windows - llama-benchy: llama-bench-style LLM benchmarks for any OpenAI-compatible endpoint
If, like me, you run your models locally and sovereignly, you know the problem: I want to know how fast a model really is on my hardware and not as a theoretical figure, but the way it actually reaches me as an end user. For exactly that, the llama.cpp world has the popular tool llama-bench.… Read more: llama-benchy: llama-bench-style LLM benchmarks for any OpenAI-compatible endpoint - Fully Local Web Search – How I Wean My Hermes Agent off the Cloud Drip
My Hermes Agent has been able to search the web and extract page content for a while now. Until recently I handled that with Tavily for search and a self-hosted Firecrawl for extraction. The setup worked flawlessly, right up until my Hermes Agent had burned through the free 1,000 API requests to Tavily. And one… Read more: Fully Local Web Search – How I Wean My Hermes Agent off the Cloud Drip - Animated Architecture Diagrams with D2 and ffmpeg – the Foundation for an AI-powered Diagram Generator
Anyone documenting complex infrastructures quickly hits the limits of static diagrams and MS PowerPoint as tools. A setup consisting of multiple machines, two different LANs and a handful of Docker containers can certainly be described in text with many sentences – but an animated diagram that actually shows the data flow is much faster for… Read more: Animated Architecture Diagrams with D2 and ffmpeg – the Foundation for an AI-powered Diagram Generator - Firecrawl in Your Own LAN: Sovereign Web Scraping with a Local Ollama Server
It has been itching me for quite a while: Firecrawl self-hosted, in my own LAN, with no cloud dependencies, connected to my local Ollama server. Web scraping is one of the key capabilities a AI agent needs if it is supposed to do serious research and also have access to up-to-date information from the internet.… Read more: Firecrawl in Your Own LAN: Sovereign Web Scraping with a Local Ollama Server
The tutorial offers a clear and practical guide for setting up and running the Tensorflow Object Detection Training Suite. Could…
This works using an very old laptop with old GPU >>> print(torch.cuda.is_available()) True >>> print(torch.version.cuda) 12.6 >>> print(torch.cuda.device_count()) 1 >>>…
Hello Valentin, I will not share anything related to my work on detecting mines or UXO's. Best regards, Maker
Hello, We are a group of students at ESILV working on a project that aim to prove the availability of…