Launched this week
Clusy
AI notebook platform for modern data science
166 followers
AI notebook platform for modern data science
166 followers
Clusy is an agent-native notebook platform for researchers and data teams to build, branch, run, and evaluate ML and data science workflows in the cloud. Describe a goal in natural language, and Clusy plans the workflow, sources datasets, preprocesses data, runs parallel experiments in replicated kernels, compares model architectures, and helps produce optimal models through a human-in-the-loop notebook experience.
Free Options
Launch Team / Built With
love how the natural language goal actually gets decomposed into a full workflow with branching and parallel runs, that agentic notebook loop feels really thoughtful compared to the usual "chat with your data" wrappers.
Clusy
@yegendilar30632 that is exactly what we wanted!
Tried Clusy over the weekend and the branching workflow actually changed how I compare model runs instead of just stacking notebooks in a folder. Liked that it suggested preprocessing steps I hadn't considered for my dataset.
Clusy
@muhammed512501 glad to hear that it helped!
Spent an hour branching off a sentiment classification task and was surprised how smoothly it ran three model variants in parallel without me babysitting kernels. The natural language planning actually picked a reasonable preprocessing pipeline on the first try.
Clusy
@iuraf1721 glad it helped!
The branching workflow feels like it was designed by people who have actually wrestled with messy experiment trees in Jupyter at 2am. The replicated kernels running parallel comparisons is a clever fix for the whole "rerun everything from scratch" pain.
Clusy
@didem482549 hahaha although this seems like an LLM response, it is pretty on point
Tried branching a notebook into a few parallel experiments and it just worked without me babysitting the kernel setup. The natural language goal thing still feels a bit magical when it actually picks a sensible dataset.
Clusy
@erdem522541 cool! glad to hear it worked for you, open to any feedback
tried branching a few experiments last night and the parallel kernel runs actually felt snappy, not the usual cloud notebook lag. the natural language to workflow step was a neat surprise too.
the natural language goal thing actually worked better than i expected, it pulled a clean dataset and spun up a few models in parallel without me babysitting it. comparing architectures side by side in the notebook was the part that sold me.