Claire Vo · 2 min read · Gen AI Tools
This solo builder runs 24/7 local AI on his own hardware | Alex Finn
Read the original on lennysnewsletter.com →
This episode spotlights Alex Finn, a solo AI builder who runs a 24/7 local AI setup across multiple machines (Mac Studio, DGX Spark, RTX 5090) coordinated by a self-built fleet dashboard. It covers how he maps specific models to hardware, wires them into Claude Code loops, and achieves a software factory that runs without babysitting through OpenClaw, Hermes, and Tailscale.
Key Takeaways
- Local hardware fleets paired with a software factory enable continuous 24/7 AI tasks without relying on cloud subscriptions.
- Different hardware (Mac Studio, DGX Spark, RTX 5090) have distinct strengths and roles that can be allocated by task.
- Tailscale enables secure, centralized fleet control and management across multiple machines.
- OpenClaw and Hermes power distributed agents with failover, improving reliability and uptime.
- A well-designed fleet dashboard, along with build and review loops, supports efficient task allocation and continuous improvement of local models.
Excerpt
Alex Finn is an AI builder, YouTuber, and the creator of Vibe Code Academy, a community for people learning to build with AI tools. He runs one of the most ambitious local AI setups I’ve come across: three Mac Studio 512 GB machines, a DGX Spark, and a custom RTX 5090 build, all coordinated through a fleet dashboard he built himself. He’s spent five months figuring out which local models belong on which machines, how to wire them to Claude Code loops, and how to get a software factory running without babysitting it. Listen or watch on YouTube , Spotify…