the world's first prod-grade auto router powered by @typesafeai 's jev and @OpenRouter
ship on friday night 6:30 pm they say
lfg
on track to 500 trillion token month
just getting started
i get many many dms every week on being onboarded as a provider to openrouter
we allow only the top & most trusthworthy providers so our customers know their privacy is ensured
devin by @cognition is the best all in one package right now
and it's not even close
so many things i use of it just makes me think "this makes so much sense, how did no one think of this before?"
it's the bar to reach for any local/cloud aio agent
Show more
jesus christ
i implore you to run ori eval inside devin
and setup an automation to re-run it every month to always be using the best model for YOUR specific use case
this is like a chatgpt moment for model evals for me
Show more
another benefit to cloud agents is
you just set it up once
and you can add other ppl to help you build your biz
no need to ask them to set local agents up + share/add all the keys (most annoying part) + inherit all ur org's skills/settings/blueprints/instructions/ etc
Show more
dang
im getting pilled that cloud agents, not local cli, is the future
it also needs shared context, GOOD memory, connected to ALL your services (especially logs), etc
we're hiring cracked evals/benchmarking ppl
research-oriented role
super tough hairy unsolved problems
those that thrive in unknowns preferred
pls dm me with your actual work (not resume), will fast track you
Show more
gemini 3.7 flash on @OpenRouter has an exclusive 50% discount with google gemini on top of the existing 50% discount
enjoy!
openrouter is the exclusive partner for muse spark 1.2
and it's a really good model!!
whoever shared the "i have adhd" skill with me
thank you
it's made my claude replies so good
hot take: choosing the best coding model is easy
but for everything else - translations, summarization, data extraction, etc - it's all based on vibes
we just shipped task type insights on @OpenRouter mcp - see what models ppl are using for specific tasks, backed by prod usage
Show more
i had a BURNING question about ai models as an ex-pubg/apex comp player
what if you threw them into a battle royale game, gave them the tool calls like attack(), walk(), etc, and let them go wild?
well, today, "royale: last agent standing" answers this Q
watch the games đđģ
Show more
