Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
m-ric 
posted an update 2 days ago
Post
3696
Since I published it on GitHub a few days ago,
Hugging Face's new agentic library 𝘀𝗺𝗼𝗹𝗮𝗴𝗲𝗻𝘁𝘀 has gathered nearly 4k stars 🤯

➡️ But we are just getting started on agents: so we are hiring an ML Engineer to join me and double down on this effort!

The plan is to build GUI agents: agents that can act on your computer with mouse & keyboard, like Claude Computer Use.

We will make it work better, and fully open. ✨

Sounds like something you'd like to do? Apply here 👉 https://apply.workable.com/huggingface/j/AF1D4E3FEB/
sauravpanda

I love this idea, I am also starting a project using transformer.js to automate things in browsers like computer use. I would love to see if you guys have any plans for the same.

evilfreelancer

Sounds like https://flowiseai.com/

sdalemorrey

I’ve been working with smolagents since you released it and I’ve got to admit I like it but don’t love it.

It’s already running in a restricted environment and I’ve personally got it running isolated in a docker container.

It would be a lot more useful if there were a way to signal to the CodeAgent that all imports are ok and just let it rip. As it is, it’s been super creative with solutions but then I have to stop it and manually add the imports (which can get quite lengthy).

Maybe considering just how large the Python ecosystem is and how creative DeepSeek can get, it would be best to have a black list of things that can’t be imported instead of or in addition to the current whitelist.

Another thing that would be helpful is if it could give a report on what agents it did code and where they are stored so I can examine them. I’m sure they’re somewhere but I’m having a lot of difficulty tracking them down.

In this post