Clusy

Clusy is an AI IDE for Jupyter notebooks in which an embedded agent plans work, writes and runs notebook cells on cloud CPUs or GPUs, and returns results that can be inspected, edited, and re-run. The system keeps every step visible in a real notebook so code-level control remains. Users describe the desired outcome in plain language, and the agent handles execution within the notebook context.

Clusy operates in a browser without requiring installation, providing a chat alongside the notebook interface. The agent coordinates data loading, code writing, execution, and decision making, while users steer by replying in chat or editing cells themselves. Branching lets users fork experiments and run them in parallel without recomputing loaded data.

Notebooks remain compatible with the .ipynb format and can be committed to GitHub, downloaded, or published to Hugging Face and Kaggle. Notebooks can be exported back to .ipynb, and content can be loaded from external data sources and databases. The tool emphasizes keeping the output as a readable, editable notebook that can be exported.

Clusy supports readers who work with data and models, including analysts, data scientists, ML engineers, and researchers, with a requirement to read Python and a DataFrame and know roughly what to find; the agent does the typing and the user makes the calls.

Use cases

• analysts, data scientists, ML engineers, researchers working with data and models