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.
Clusy is finally live! Sign up today for free, try our platform, and let us know what breaks.
We built Clusy for ourselves with a lot of care, and are now launching to share it with the world. If you are using Jupyter or Google Colab (or any other Python notebook) in your work, we believe that Clusy can help optimize your productivity at almost no friction or migration cost.
We started building because the way people work in notebooks has not really caught up with what AI now makes possible. Jupyter and Colab have been amazing, but we think the next generation of notebooks should feel much more goal-driven, collaborative, and agent-native. Therefore, Clusy is built around the end-to-end approach to data science - our agent works alongside you to help across the whole pipeline, starting from your idea and environment setup to actual model training and deployment.
Sign up for a free plan or use CLUSYLAUNCH to get 50% off for the first 3 months!
Eldar, having an assistant right there while I stay in the driver's seat is exactly what I would want from a notebook. So much of this work is fiddly setup and dead ends, and smoothing that out sounds great to me.
The replicated-kernel branching is the part I'd want pricing clarity on before going deep. If I fan out into say 5 parallel branches to compare architectures, am I paying for 5x compute running concurrently, or does the platform queue/throttle branches on the free and paid tiers? Trying to figure out if this is something I can use for quick exploration without watching a meter the whole time.
The branching experiments workflow feels like the standout feature here, finally a clean way to compare model variants without losing track of versions. Setup was smooth and the parallel kernel runs saved me real time on a small benchmark.
how does branching actually work under the hood, can i diff notebook states like git commits or is it more of a workflow level fork
The idea of branching notebooks like git repos is something I've wanted for years. Mixing that with parallel experiments in replicated kernels means finally getting a real comparison view without copy-pasting cells everywhere.
How does Clusy actually decide when to branch a workflow versus just continue in the same notebook, and can I override those branching decisions with my own logic?
Curious how the "agent-native" piece actually plays out in practice, does Clusy suggest next steps on its own or do I still have to drive the branching and comparisons? Also wondering what happens when an experiment fails halfway through a parallel run.
how does the branching actually work under the hood, like can i fork an experiment midway and rerun only the changed cells without burning through compute on the whole pipeline again?
How does the "agent-native" planning actually handle steps where I need to bring in proprietary data sources or private models that aren't publicly available?
Tried branching a quick experiment and the parallel kernels saved me a ton of switching time. The natural language goal setup actually picked a reasonable baseline model for my dataset.
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.
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 branching notebook workflow is a really sharp call, letting us fork experiments without losing state feels like how ML work should actually flow.
How does the human-in-the-loop part actually work when the agent is branching off into parallel experiments. Do you step in between runs or only after the comparison view comes back?
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.
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.
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.
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.
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.
About Clusy on Product Hunt
“AI notebook platform for modern data science”
Clusy launched on Product Hunt on July 1st, 2026 and earned 107 upvotes and 49 comments, placing #23 on the daily leaderboard. 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.
Clusy was featured in Developer Tools (515.4k followers), Artificial Intelligence (473.1k followers) and Data Science (3.8k followers) on Product Hunt. Together, these topics include over 181.1k products, making this a competitive space to launch in.
Who hunted Clusy ?
Clusy was hunted by Eldar Hasanov. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Clusy stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Eldar Hasanov