sandboxd
Open-source, self-hosted AI app builder.
Prompt it and a coding agent builds real apps in isolated sandboxes on your
server — each live at a preview URL. You own the infra, code, and data. MIT.
🔥 Trend of the Day on Trendshift
Prompt → a real, running app on your server, at its own URL.
See it in action 👇
1 · Build from a prompt — an agent builds it in an isolated sandbox, live at a preview URL. | 2 · Or run an existing app — n8n, Ghost, Grafana… 80+ curated apps, one click. |
3 · Or drive the API — every action is a /v1 call, headless & scriptable. | ▶ Try the live demo Click around a real console with sample data — no install. |
📣 Stay in the loop
Self-hosting is MIT and free, forever — git clone and you're done.
Want the 1.0 release + occasional product updates, or a managed cloud so you don't run the box yourself? Two links:
No spam, one-click unsubscribe, and the cloud is optional — the self-hosted engine is always the full product.
What is sandboxd?
The apps where you type "build me a todo app" and a working site appears at its own link — Lovable, Bolt, v0, Replit. sandboxd is the open-source engine that makes that work, on your own server. One HTTP request and it:
- spins up a private, isolated container (its own filesystem + limits),
- runs an AI coding agent inside it against your prompt, and
- hands the app a live preview URL.
Idle sandboxes sleep and wake on demand, so one ordinary box holds many apps instead of a VM each. Under the hood it's deliberately small: one Go program driving Docker, Traefik for URLs, SQLite for state — no Kubernetes, no separate database, no queue.
Two ways to use it
- API-first — everything is a
/v1call, so you can build sandboxd into your own product. - Optional web console — the fastest, no-code way to use it hands-on:
create an app, chat to a coding agent, watch the live preview, edit files, and
review a git diff & push — all in a browser. It's a pure
/v1client; the engine runs perfectly headless without it.
New here? Start with the console. Building a product? Drive the API.
What can you run? (a lot — from one console, no code)
The console isn't only for coders. Open it and, in one click or one prompt, you can:
- 🚀 Run a ready-made open-source app — a Ghost blog, n8n automations, a Gitea git host, Grafana / Metabase dashboards, Uptime Kuma, Jupyter, Keycloak… 80+ curated apps, installed and live at their own URL.
- 🧩 Start from a starter — a React/Vite, Next.js, or FastAPI scaffold that boots to a live preview; then just chat to shape it.
- 📥 Bring your own repo — import any public Git repo (no credential needed) and let a coding agent work on it.
- ✨ Build from scratch — describe an app and watch the agent build it in the live preview, then commit & push.
This is just a taste — if it's open-source, you can almost certainly run it.
Any Node, Python, or static-binary app boots as-is; anything else, bring your own base image or preset.
Ways to run an app → · Base image, stacks & presets · Architecture
Dev → prod, never shorter: prompt an app into a sandbox, iterate on a live preview, then self-host it on your own server in one command.
Quick start
Needs Docker + the Compose plugin and git on Linux (macOS via Docker Desktop is best-effort). Runs natively on amd64 and arm64 — including Apple Silicon Macs and arm64 Linux hosts (e.g. AWS Graviton) — every image builds from multi-arch bases with no cross-compilation. Install in one line:
curl -fsSL https://raw.githubusercontent.com/tastyeffectco/sandboxd/main/install.sh | bash
It builds the images, starts the stack with the web console, and prints your console URL + a generated login — no password step. Open it, connect an agent under Settings, create an app, and build. No code needed.
- Console:
http://console.localhost— the installer prints your login; lost it? run./console-login.shto see it again anytime - API:
http://127.0.0.1:9090(curl http://127.0.0.1:9090/healthz→ok) - Headless (no console): run with
SANDBOXD_CONSOLE=0(or--no-console) - Upgrade later: run
./upgrade.sh— it backs up your database first, health-checks the new version, and rolls back automatically if it fails (Upgrading)../upgrade.sh --checkshows your version.
Prefer the API? Connect an agent once, create a sandbox, hand it a prompt:
API=http://127.0.0.1:9090
curl -s -XPOST $API/v1/agents/claude-code/api-key -d '{"api_key":"sk-ant-..."}'
ID=$(curl -s -XPOST $API/sandbox -d '{"ports":[3000]}' | sed -E 's/.*"id":"([^"]+)".*/\1/')
curl -s -XPOST $API/v1/sandboxes/$ID/tasks -d '{"prompt":"build a todo app on port 3000","agent":"opencode"}'
# open the result at http://s-$ID-3000.preview.localhost
Full walkthrough → sandboxd.io/quickstart.
🚀 Deploy to a VPS in one click
sandboxd needs one Linux server with Docker — nothing else. Grab a server below (2 vCPU / 4 GB is plenty to start), paste our cloud-init file at creation, and it installs itself.
Disclosure: we earn a referral commission when you sign up through the provider links below, at no additional cost to you. It helps fund sandboxd's development.
Then on the new server (or paste deploy/cloud-init.yaml as user-data and skip this):
curl -fsSL https://raw.githubusercontent.com/tastyeffectco/sandboxd/main/deploy/bootstrap.sh | sudo bash
Full per-provider walkthrough: deploy/DEPLOY.md.
What you get
- Isolated sandboxes — a hardened container per app with a workspace + live preview URL; sleep/wake so idle apps cost nothing.
- Built-in agents — OpenCode & Claude Code. No credential ever enters a sandbox (a proxy injects it on the wire), and every task is checkpointed & revertible.
- Runtime presets — React/Vite, Next.js, Node/Express, FastAPI, Worker; boot to a preview and reload after agent edits.
- Files, Git & secrets — in-browser editor + diffs, commit & push, per-app config/secrets (encrypted, write-only).
- Snapshots / fork / restore, an activity timeline, per-process logs, and live lifecycle tuning.
Who's it for?
✅ Use it if you run many sandboxes for other people — an AI app-builder, an agent platform, a coding playground, per-user or per-branch preview environments, or team multi-app hosting.
❌ Skip it if you just need one or two containers for yourself — a shell
script or docker run is simpler.
(Why not just a script?)
Managed — we run it for you
Don't want to run the server yourself? We'll install, configure, and manage sandboxd on your own box — BYOC (your compute, your data, no lock-in). One-time setup + optional monthly management. See Managed →
Documentation
Full docs live at sandboxd.io:
Building on it from your own agent? AGENTS.md is a
copy-pasteable runbook.
Roadmap & community
- 🗺️ Roadmap — what's shipped & next · public project board
- 💬 Discussions — ask & get self-hosting help
- 🤝 Contribute — good first PRs: add a runtime preset or an App Store recipe (
CONTRIBUTING.md) - 🔒 Security — report privately per
SECURITY.md
Beta · 0.x. Container isolation (not VMs), single-server, and API auth off by default — all fine for your own users; tighten before untrusted multi-tenancy. See Hardening. Expect the occasional breaking change before 1.0 — pin a version and update as you go.
⭐ If sandboxd is useful, star it
Stars are how other builders find sandboxd — it's the fastest way to support the project (and it keeps us going). Thank you 🙏
License
MIT. Use it, ship it, sell what you build on it.
Sponsors
sandboxd is free and MIT-licensed. Sponsors keep it maintained and fund the deploy roadmap — thank you to everyone who chips in.
No sponsors yet — be the first.