← Back to context

Comment by benno128

5 days ago

Working on Runno (https://runno.dev/) as a side project. It's a tool for running code in the browser for educational use.

[Edit]: I wrote a re-introduction to Runno: The WebComponent for Code over the weekend (https://runno.dev/articles/web-component/)

I've been playing around with turning it into a sandbox for running code in Python (https://runno.dev/articles/sandbox-python/). This would allow you to safely execute AI generated code.

Generally thinking about more ways to run code in sandbox environments, as I think this will become more important as we are generating a lot of "untrusted" code using Gen AI.

3 comments

benno128

Reply
kmad  5 days ago

Awesome! Have you considered pyodide[1]? Pydantic uses this for sandboxing its AI agents [2].

1. https://pyodide.org/en/stable/ 2. https://ai.pydantic.dev/mcp/run-python/

  • benno128  5 days ago

    Thanks! Yeah I'm very aware of Pyodide and interested in adopting some of their techniques.

    A big difference between my approach and their approach is that Runno is generic across programming languages. Pyodide only works for Python (and can only work for Python).

    Big interesting development in this space is the announcement of Endor at WASM IO which I'd like to try out: https://endor.dev/