Skip to main content

Introducing sandboxd

· 3 min read
The sandboxd team
The sandboxd team
Maintainers of sandboxd

Think of the apps where you type "build me a todo app" and seconds later a working website appears at its own link — like Lovable, Bolt, v0, or Replit. sandboxd is the open-source backend that makes that possible, running on your own server.

One HTTP request, three things​

You send sandboxd one HTTP request, and it:

  1. Creates a sandbox — a private, isolated Linux container (its own filesystem, its own memory limits), so one user's code can never see or break another's.
  2. Runs an AI coding agent inside it — you give it a prompt, and it writes the code into that sandbox. The OpenCode and Claude Code CLIs come pre-installed.
  3. Gives the app a live URL — the dev server running inside the sandbox is instantly reachable at a shareable preview link.
POST /sandbox          → a private, isolated container spins up
POST .../tasks         → an AI agent writes an app inside it
http://<id>.preview... → that app is live at its own URL

Cheap to run, by design​

A sandbox goes to sleep when nobody's using it (freeing memory) and wakes up the instant someone opens its link again — files are saved on disk the whole time. So one ordinary server can hold many users instead of needing one virtual machine each. That's the difference between a $20 server and a $2,000 cluster.

Boring on purpose​

Under the hood it's deliberately small and easy to understand: one Go program that tells Docker what to do, with Traefik handling the URLs and SQLite as the database. No Kubernetes, no separate database server, no message queue — you could read the whole control plane in an afternoon. A reconciler converges Docker back to the database on every boot, so it survives crashes and restarts.

Who it's for​

If you're building an AI app-builder, an agent platform, a coding playground, or a per-user preview product, the hard part isn't the prompt — it's the infrastructure underneath it: multi-tenant isolation, per-user preview URLs with routing and TLS, idle/wake cost control, agent orchestration, and persistence that survives reboots. That's months of platform work, and sandboxd is that platform, distilled to one command.

And if you just need one or two containers for yourself? Honestly, a shell script or docker run is simpler — use that. sandboxd earns its keep when you're running many sandboxes for other people.

Get started​

git clone https://github.com/tastyeffectco/sandboxd.git
cd sandboxd
./install.sh

That's it — the API is live at http://127.0.0.1:9090, and your first agent task is one curl away. Head to the quickstart for the full install → agent → preview walkthrough.

sandboxd is self-hosted, MIT-licensed, and built to be read and extended. Use it, ship it, sell what you build on it — star it on GitHub.