hey! we'll build the same thing but just open source it and make it free :)

if you go to gumloop.com/mcp all these servers are hosted for you with auth handled via your free gumloop account.

Definitely at some point in the near future! started with python for now just because we had to pick a lane but we'll be porting them all over one day

actually made me laugh. will be using this in the future

nice breakdown

AgentHub.dev | Vancouver Canada or SF | Full-time | ONSITE | Founding Frontend/UX Engineer

AgentHub's a platform for automating complex tasks with AI via a drag and drop interface.

We're a team of 2 founders currently and just finished the YC W24 batch. We've grown from 0 to 10s of thousands in monthly revenue in the past 4 months and want someone to join us and help lead frontend dev/help improve overall platform UX.

Job posting: https://www.ycombinator.com/companies/agenthub/jobs/iIpDrPG-...

We think we can raise a series A and seriously scale with a small handful of people, just looking for the right ones!

Techstack for frontend: React, Typescript, Tailwindcss, Redux

Email us at careers@agenthub.dev or apply via that job posting link.

This is one of the few products I can say I actually love. Congrats on the launch guys!!

Thank you!

Thanks! They look great as well, I've never heard of them before so thanks for the link. We definitely have a vision where where we want to go but unsure where that will diverge from competitors. Focused on just building things people want at the moment :)

The starter plan is generally for experimentation purposes and for those who only need the less powerful models (GPT 3.5, gemini pro, perplexity 70b). Everyone on the pro plan can add their own API keys and unlock unlimited AI calls.

oh dang. Dalle prompt restrictions changing make older templates like that break. We'll adjust the default example to avoid that. Thanks for the callout

Yeah... DALLE is super annoying about this now. I had the same problem in my little "AI trailers" toy project [0], and it can usually be fixed by just checking for that specific "content policy" error when DALLE fails -> passing this into GPT: "Rewrite this prompt so that it passes the content policy: {prompt}" -> and then retrying with the updated prompt.

It's kinda dumb, but it's a quick fix that might help ¯\_(ツ)_/¯

[0] https://aitrailers.xyz/

Great tip, we'll definitely try and use this as a fail safe. Thanks!