Building This Site with Hermes Agent
From a blank Astro project to a deployed site in one session. Here's how an AI agent wrote the code, generated the content, and pushed to production.
Local LLMs, full-stack engineering, and cloud infrastructure — elect-rix builds autonomous systems and ships products that scale.
I'm a solo builder running a two-workstation AI lab. One machine handles local LLM inference with Ollama and 16GB VRAM. The other manages distributed builds and GPU compute. Everything is self-hosted, private, and fast.
I build autonomous AI agents, full-stack web applications, and cloud infrastructure. My tools are local-first — your data never leaves the box unless you want it to. From prototype to production, the Workstation Duo delivers.
End-to-end engineering — from AI agents to production deployments.
Connect LLMs, agents, and ML pipelines into your products. Local or cloud — your data stays yours.
React, Astro, Node, Python — clean architecture, typed APIs, and performance that scales.
Deploy anywhere. AWS, Cloudflare, self-hosted. CI/CD, IaC, and automated workflows.
Strategic technology decisions, architecture reviews, and hands-on mentorship for your team.
Projects shipping from the Workstation Duo.
Autonomous AI assistant deployed on Telegram. Manages coding tasks, research, and DevOps — 24/7.
This site — Astro, Bun, Tailwind. Built locally, deployed to Cloudflare Pages, generated with AI.
Two-machine setup: local LLM inference, distributed builds, GPU compute, and self-hosted services.
Experiments, tutorials, and lessons learned.
From a blank Astro project to a deployed site in one session. Here's how an AI agent wrote the code, generated the content, and pushed to production.
Raw commentary, updates, and behind-the-scenes thoughts from the Workstation Duo project.
The first post, written by local AI and pushed live from a basement workstation — a proof of concept for the elect-rix.tech pipeline.