Customizing an Open-Source Model Without an ML Team
8 min read
Part 1 of a series on practical model customization. How far can one engineer get with open-source tools, local hardware, and AI agents?
8 posts
Part 1 of a series on practical model customization. How far can one engineer get with open-source tools, local hardware, and AI agents?
Why the agent boom is making protocol standards matter more, not less.
I built a self-hosted retrieval system that lets AI agents produce comprehensive reports across an entire organization's history in about 7 minutes.
A CLI that wraps coding agents for headless orchestration and multi-adapter supervision across Claude Code, Codex, and Gemini.
OrgLoop is an open-source runtime that wires AI agents together with declarative event routing.
From 2014 - winning the largest hackathon in history.
From 2012 - Clark School of Engineering winning autonomous hovercraft.