AI Development Frameworks
How Flowise works under the hood: the architecture explained
Flowise turns visual nodes into executable LLM pipelines. Here's how the drag-and-drop flows actually execute, what…
Blog
All Articles
Cybersecurity assessments, awareness training, threat intelligence, tabletop exercises, and expert guidance for your organisation.
Local LLMs
LocalAI on my homelab: running OpenAI API locally
I set up LocalAI to replace cloud LLM calls in my automations. Took about an hour,…
AI Development Frameworks
I moved from raw prompt chains to LangChain. What actually changed.
Built a few LLM tools the hard way first. Then tried LangChain. Some surprises. Some things…
Self-Hosted AI Apps
SillyTavern on my homelab: the install I wrote down
Setting up a local character chat interface. I've done this three times now. Here's what actually…
Local LLMs
Jan feels like software that respects your machine
I ran Jan locally for two weeks. It's not trying to be ChatGPT. It's trying to…
Self-Hosted AI Apps
ComfyUI + Home Assistant: Triggering image generation from automations
Wire ComfyUI into Home Assistant so your automations can generate images on demand. The setup that…
AI Coding Tools
What Tabby is really doing when you hit autocomplete
I installed Tabby on my homelab today. Here's what actually happens between your keystroke and that…
AI Hardware
Hailo-8L on Raspberry Pi 5: the install I keep notes on
Adding a 13 TOPS AI accelerator to your Pi 5 is straightforward until it isn't. Here's…
AI Automation
Activepieces on my homelab: the config that actually runs
I set up Activepieces behind Traefik this morning. Here's the docker-compose, environment file, and reverse proxy…
Local LLMs
What Open WebUI is actually doing when you click send
The architecture behind Open WebUI's chat interface. Request routing, vector storage, model inference—how it all connects.