Launching Jev on Command Code for free today. Jev x Command Code is super interesting. You can only use Jev in headless mode or Provider API. Also open sourced a mod "cmd-mod-jev-nudge" Use Jev for free to keep your agent running as long as the there's more work to do.

Here's the open sourced mod for continuation nudge, have at it. mix and remix. got the prompt from @willcb: 'Would a gentle nudge help the agent advance useful work within the user’s existing request right now?'

Welcome Jev!! 🐐

I still don’t understand its usecase

have you watched the video?

It's Jev time in Command Code.

🤘

wow

🤘

You're awesome, @MrAhmadAwais feature is going to give Command Code a huge advantage...

Let's go, GOAT! 🐐

So good

Let's go! 👊

Hey Jevis

What’s your best Jev use case internally? Would love to see how a pro uses it

Have you read this? Taste is quite similar to Jev.

Nice. But too bad that there is no proper ADE support for command code. People are forced to use the API instead of the actual harness because of this

you're misinformed. check out @CommandCodeAI Desktop

Even paying for the GOAT plan I only have 200 reqs/day? 😓

free limits are 200/day and the upstream has no GPU capacity so we can't really sell more either. looking into it.

I don’t mind being charged in my goat plan 😆

i know. let us get the capacity for it. @AhmadBilalDev

@AhmadBilalDev

让代理别忙一半就停，这个小模组还挺对症

I tried using JEV in CommandCode on the Go plan, but it doesn’t work there. It would be really nice if JEV could also be supported on the Go plan.

Upgrade to GOAT. $1 isn't a serious plan.

Limited time or staying free? 😳

few days, it's pretty cheap otherwise too.

Yeah very cheap!

Final phases usually make leaderboards more interesting to watch because rankings can change quickly. BingX has three separate categories here, which gives the results more context.

It's a great demo and that's a great example. I think you can also try to incorporate or create a mod that can help people switch models or their effort based on the complexity of the task. Even while it's working, like during the single run.

you can ask, @CommandCodeAI it can build mods for you.

@CommandCodeAI Oh is it! okay thank you so much I'll do that, I'm testing.

headless agents are great, pair them with tinyfish monitor so they only run when something actually changes