2025-09-30 –, Louis Armand 1 - Est
JupyterLite brings Python and other programming languages to the browser, removing the need for a server. In this talk, we show how to extend it for AI workflows: connecting to remote models, running smaller models locally in the browser, and leveraging lightweight interfaces like a chat to interact with them.
JupyterLite makes it possible to run Jupyter notebooks directly in the browser, using WebAssembly. This opens the door to new workflows, where AI models are accessible without any backend infrastructure.
In this session, we will cover:
- Running a Jupyter distribution in the browser with JupyterLite, building on the JupyterLab framework
- Connecting to remote AI models from the browser
- Running models locally using WebGPU and WebAssembly
- Interacting with conversational agents and other collaborators via the chat panel
- Handling authentication and browser constraints
- The case of privacy: keeping data on the user’s device, and giving users more control over their interactions with AI models
Technical Director at QuantStack and Project Jupyter core developer and maintainer (JupyterLab, Jupyter Notebook, Voilà Dashboards).
