havent seen many people outside anthropic ultracode yet. this thing is scarily good at burning tokens but you need to set up your repo to parallelize properly to make use of the fanout that i think subagents are best at.
basically the idea is "subroutines but intelligent". when you undersatnd just how much knowledge work is just yakshaves after yakshaves that require some judgment and intelligence, you start to appreciate that dynamic workflows are not just for coding tasks...
OpenCode 1.17.3 can reference other git repos or local folders
ππππππππππ: {
"ππππππ": "ππππππ.πππ/π΄πππππ-ππ/ππππππ-ππππ"
}
gives it full access to the effect codebase, here's how we use it
Things that make your codebase legible to agents (learned the hard way):
1. One source of truth. No content hiding in a CMS the agent can't see
2. Names that say what they do
3. Tests that double as docs
4. Delete dead code. Agents trust it like it's load-bearing
Vercel AI Gateway recovers on average over 1T tokens a month π€―
Much like Stripe recovers revenue with smart retries on failed payments or credit card updates.
And we do it with 0οΈβ£ zero markup over the labs; adding redundancy, zero-data retention enforcement, observability, usage APIs, caps, β¦
https://t.co/OougSipbBX