Run Stan models directly in your browser.
Stan Playground is a browser-based editor and runtime environment for Stan models. Users can edit, compile, and run models, as well as analyze the results using built-in plots and statistics or custom analysis code in Python or R, all with no local installation required. This is well-suited for teaching and learning purposes and for users who want to experiment with Stan models without the hassle of setting up a local environment. You can also share your results with others using the GitHub Gist feature.
While the Stan models execute in the browser (on your local machine), the compilation process requires a dedicated server. We provide a default public server for your convenience, but you can also set up your own compilation server either locally or remotely.
Announcement post: Stan Playground: Stan without installing Stan
The features of Stan Playground are documented on Github Pages. See there for information on customizing the website, preparing easy-to-share links, embedding it in your own page, and more.
The compilation server is a FastAPI project with a dockerized environment
located in the backend/ folder.
The README there describes the server architecture and
how one can build the docker image from scratch.
The website frontend is a Vitejs/React project located in the gui/ folder.
The README there gives information on how to get started running a local development server.
Apache License 2.0
Center for Computational Mathematics, Flatiron Institute