Hollis Nolan

Jeremy Sebastian replying to your post, cant seem to comment images back.

I built a multi model, multi backend (lmstudio, lama.cpp, vllm, hermes...), test harness. Not only does the harness have to plug and unplug every viable OSS model I can find, it also has to be built via multiple platforms. Been mixing Claude Code, Codex and Beam for that.

All are in a json lines chat room, and asking eachother things, declaring that they are doing things....

For this project, zero human review of any pull request. And, very few role definitions upfront.

I am letting the room decide.

of course paired with local, personal brains, pile o md files into a wiki. Created and curated via oss or local models. Frontier cloud available if you want but not needed. Consulting and building for supply chain and warehouse full of widgets customers. No subscriptions from me, own you AI stack, own your IP. At the end of the day, 10+ years in data science and a team of implementors. Which stack best suits your exact case.

Ask me where 1/4th of my house's energy bill went, or why the basement is 85 deg.