I’ve been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics …
6th June 2026
I’ve been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics I’ve been looking for. I’ve released it as an alpha package called micropython-wasm, and I’m using it for a code execution sandbox plugin for Datasette Agent called datasette-agent-micropython.
Why do I want a sandbox?
What I want from a sandbox
WebAssembly looks really promising here
There’s a jargon-filled headline for you! Everyone’s building sandboxes for running untrusted code right now, and Pydantic’s…
Building the Pluggable Sandbox I'm building an agent harness, as a learning project and...
I've been on sabbatical for a few months. Writing code. Building projects. And running Docker...
Six weeks ago, running code on jhansi.io meant curl + sandbox IDs + manual cleanup. Today it looks...
I got annoyed. I was looking at how most code execution platforms handle sandboxing and kept seeing...
A deep dive into building stateful agents using TensorLake sandboxes, measuring latency, and handling computer use challenges.
I got tired of running Docker manually. So I built a sandbox for AI-generated code.
pip install jhansi — the SDK is live
Building a Secure Code Execution Sandbox in Rust
BoxAgnts Runtime (3) — WebAssembly: A Better Sandbox for AI Agents
Run AI Coding Agents Safely with Docker Sandboxes
Why file-system agents are essential for AI tools to truly extend your codebase
What is Sandbox Security? | Docker
BoxAgnts Tool System (2) — The Security Model of Wasmtime Sandboxing
Microsoft launches MXC, an OS-level sandbox for AI agents, with OpenAI and Nvidia already on board
Dropbox Nova for AI Coding Agents, OpenAI's Codex Sandbox, & Puppeteer MCP Server
