1) Curated a set of models I like and heavily optimized all possible settings, per agent role and even per skill (had to really replumb a lot of stuff to get it as granular as I liked)

2) Ported from sqlite to postgresql, with heavily extended schema. I generate embeddings for everything, so every aspect of my stack is a knowledge graph that can be vector searched. Integrated with a memory MCP server and auditing tools so I can trace anything that happens in the stack/cluster back to an agent action and even thinking that was related to the action. It really helps refine stuff.

3) Tight integration of Gitea server, k3s with RBAC (agents get their own permissions in the cluster), every user workspace is a pod running opencode web UI behind Gitea oauth2.

4) Codified structure of `/projects//` with simpler browserso non-technical family members can manage their work easier (agents handle all the management and there are sidecars handling all gitops transparent to the user)

5) Transparent failover across providers with cooldown by making model definitions linked lists in the config, so I can use a handful of subscriptions that offer my favorite models, and fail over from one to the next as I hit quota/rate limits. This has really cut my bill down lately, along with skipping OpenRouter for my favorite models and going direct to Alibaba and Xiaomi so I can tailor caching and stuff exactly how I want.

6) Integrated filebrowser, a fork of the Milkdown Crepe markdown editor, and codemirror editor so I don't even need an IDE anymore. I just work entirely from OpenCode web UI on whatever device is nearest at the moment. I added support for using Gemma 4 local on CPU from my phone yesterday while waiting in line at a store yesterday.

Those are the big ones off the top of my head. Im sure there's more. I've probably made a few hundred other changes, it just evolves as I go.

Right now my solution is to run CC in tmux and keep a 2nd CC pane with /loop watching the first pane and killing CC if it detects plan mode being bypassed. Burning tokens to work around a bug.

Still use CC at work because team standards, but I'd take my OpenCode stack over it any day.

It started as a what-if joke, but it's turned out to be amazing. So yeah, npmjs.com is just reference site for me now, and node_modules stays tiny.

And the output is honestly superior. I end up with smaller projects, clean code, and a huge suite of property-based tests from the refactor process. And it's fully automatic.

I'm finding that the extra "hand holding" that MiMo and MiniMax need isn't really "extra." The Anthropic models happily agree to a plan and then do something else entirely way too often.

With MiMo and MiniMax I'm just spreading the attention throughout the day instead of big spikes of frustration figuring out where Claude went off the rails.

We operate as a diversion program with our local department of juvenile justice, and I would definitely describe the process as transformative.

From the financial perspective alone, our local law enforcement has seen a 6:1 return on investment on restorative practices. The value of all the changed lives is immeasurable.

I can build it for you if you like.