Viewing profile — jhaugh

Cool approach for real-time verification. I built something similar for long-term behavioral patterns: https://github.com/oscarsterling/reasoning-loop

I kind of liked the old one, but after getting feedback from some other fiends in the community decided to change it. TY for the advice.

I'm running 8 specialized AI agents on a Mac Mini right now. They handle research, content strategy, writing, security audits, code, and visual design. They run on cron schedules, …

Author here. We're running this on a single Mac Mini with Claude Opus. Happy to answer questions about the architecture, agent coordination, or what failed along the way.

We built a directory for AI skills (MCP servers, agent tools, plugins) because the ecosystem is growing faster than anyone can track manually. Currently indexing 1,700+ skills. Sea…

I wrote the above!

Hey HN, I built Clelp ("Yelp for AI") because I got tired of the same problem everyone has: figuring out which MCP servers and AI tools actually work. There are great lists out the…