Brett's AI Native Development -- AI Assistant
Message LLMster
Brett Drake, C#/.NET Software Developer
The spinning head is dumb, but what was here before was marketing content created by Codex. By replacing this section of the website, all remaining content is from me, not Codex. Probably some code highlights might work here. Thinking on it...
Deployment status preview
The AI Stack
The chat above runs on a language model hosted on this Mac mini. Apple silicon's unified memory makes it a compact and capable AI server.
Each prompt travels through my C#/.NET API, across my local network, and into LM Studio's llmster, which serves the model.
I initially configured google/gemma-4-e4b with its
Enable Thinking option turned on. Although the model
supports reasoning, the additional thinking produced extremely long
response delays in my setup, so I disabled it for this application.
The model returns Markdown-formatted text. To preserve the responsiveness of the streaming interface, each chunk is displayed immediately as it arrives. Once the complete response has been received, the accumulated text is rendered as Markdown, providing formatted output without delaying the streamed response.
How Is This Site Hosted?
Apache is the reverse proxy server. Multiple subdomains are used for different frontend implementations, with each subdomain routed to the appropriate Docker container. All of the frontends share the same backend API.
Apache and Docker Desktop for Linux make a good combination for this machine because it also serves desktop functions such as running Postman and Inkscape. An HDMI connection also runs to my living room TV.
If this were intended to be a hardened production server, Ubuntu Server with the Docker CLI would be a much more appropriate setup than Docker Desktop.
The machine itself is an older eight-core computer with 32 GB of RAM. Its capable hardware aged out of Windows 11 support, but as a Linux server it is an absolute powerhouse and is exceptionally well suited to this setup.