by madarco
Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud
# Add to your Claude Code skills
git clone https://github.com/madarco/agentboxLast scanned: 6/20/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@vitest/mocker: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vite-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "critical"
}
],
"status": "FAILED",
"scannedAt": "2026-06-20T07:50:38.234Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}agentbox is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by madarco. Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud. It has 262 GitHub stars.
agentbox failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.
Clone the repository with "git clone https://github.com/madarco/agentbox" and add it to your Claude Code skills directory (see the Installation section above).
agentbox is primarily written in TypeScript. It is open-source under madarco on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agentbox against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
Run multiple agents in parallel, with a single command, on your PC, self-hosted, or in the cloud
Works with iterm2 - cmux - tmux - Herdr

agentbox claude # launch a new VM with claude and your project inside
Full Documentation
npm -g install @madarco/agentbox
agentbox install
# Launch a new VM with claude, copy all your settings and workspace
agentbox claude
# Also install required project libraries and launch your dev server
> Run setup wizard? -> Yes
# Also use a cloud:
agentbox hetzner claude # or vercel, daytona
# Ctrl+a d to detach, claude keep going, to reconnect later:
agentbox attach 1
# To open a persistent shell inside the box:
agentbox shell 1
# Create a second box:
agentbox claude
agentbox attach 2
agentbox shell 2
# Open your web project on a .local url tunnel on your pc
agentbox url 2
# Or the in-box browser via webVNC:
agentbox screen 2
# Or connect to vscode/cursor inside the box:
agentbox code 2
# See status and quickly switch between agents:
agentbox dashboard

npm -g install @madarco/agentbox
Requirements: macOS (arm64 or Intel) or Linux, Docker (Docker Desktop or OrbStack), Node >=20.10. The first agentbox create / agentbox claude builds the agentbox/box:dev image (~1 GB, one-time).
Uses portless to give box web apps the same URL from inside the box and on the host.
| local docker | remote docker | hetzner | daytona | vercel | e2b | |
|---|---|---|---|---|---|---|
| Support | ✅ | ✅ | ✅ | ⚠️ Partial | ✅ | ✅ |
| Base image | Dockerfile | Dockerfile (on the remote) | Setup script (Ubuntu) | Dockerfile | Setup script | Dockerfile (Template.build) |
| Live snapshots | ✅ | ✅ (docker commit) |
✅ | 🧪 Experimental | ✅ | ✅ |
| Private preview URLs | ✅ (portless or OrbStack) | ✅ (portless over SSH) | ✅ (portless) | ✅ (native) | ✅ (native) | ✅ (native) |
Cloud setup (optional — skip for local Docker)
agentbox install — interactive setup wizard to choose which providers to use and configure them.agentbox vercel login — interactive Vercel Sandbox token setup, saved to ~/.agentbox/secrets.envagentbox hetzner login — interactive Hetzner Cloud token setup, saved to ~/.agentbox/secrets.envagentbox daytona login — interactive Daytona API key setup, saved to ~/.agentbox/secrets.envagentbox e2b login — interactive E2B API key setup, saved to ~/.agentbox/secrets.envagentbox digitalocean login — interactive DigitalOcean Personal Access Token setup, saved to ~/.agentbox/secrets.envagentbox remote-docker doctor <host> — run boxes on a machine you already own, over SSH. No login and no token: it connects as you, using your own ~/.ssh/config. Then agentbox docker:<host> claude.agentbox prepare [--provider daytona|hetzner|vercel|e2b|digitalocean|docker:<host>] — build the image and initial snapshot (e2b builds from a Dockerfile via Template.build())agentbox hetzner claude, agentbox hetzner codex, agentbox hetzner create, etc.<box> is optional almost everywhere — it defaults to the box for the current project, or use its short index (1, 2, …), name, or id prefix.
Create & run
agentbox create — Create and start a new agent box (Docker container with FUSE overlay)agentbox claude — Create a sandboxed box and launch Claude Code in a detachable tmux sessionAccess
agentbox url — Open a box's web app URL in the browser (even with no expose: service)agentbox screen — Open a box's VNC (noVNC) viewer in the browseragentbox code — Open a box in VS Code or Cursor via the Dev Containers extensionagentbox shell — Open an interactive bash shell in a boxagentbox open — Open a box's merged workspace in Finderagentbox logs — Print recent log lines from a box service; -f to streamagentbox dashboard — Box list + the selected box's live agent sessionInspect
agentbox list (ls) — List boxes in current project or -g for allagentbox status — Show service + task status from a box's agentbox-ctl daemonagentbox top — Live resource monitor (cpu/mem/pids/disk) for a box, project, or all boxesLifecycle
agentbox start — Start a stopped box (docker start + re-mount the FUSE overlay)agentbox stop — Stop a box (preserves the upper volume, node_modules included)agentbox destroy (rm) — Destroy a box and discard its upper volumeagentbox pause / agentbox unpause — Freeze / resume a box (sub-second)Sync & state
agentbox download — Download a box's /workspace back into your host workspace (gitignore-aware)agentbox cp <src> [dst] — Copy individual files between host and box (like docker cp; direction picked by name: prefix)agentbox checkpoint (alias checkpoints) — List and manage project checkpoints (warm box state to start new boxes from); bare command lists, checkpoint create capturesAdvanced
agentbox wait — Block until the box reports all autostart units readyagentbox prune — Clean up orphan state records (and with --all, orphan docker resources)agentbox self-update — Update agentbox, wipe the box image so it rebuilds, reload the relayagentbox config — Read / write layered config (global, per-project, workspace defaults:)agentbox relay — Manage the host relay process (status / stop / start / restart)agentbox app — Control the macOS menu-bar app process (status / start / stop / restart); install it with agentbox install trayRun agentbox <command> --help for command-specific options.
Full documentation lives at agent-box.sh/docs:
git clone https://github.com/madarco/agentbox && cd agentbox
pnpm install && pnpm build
node apps/cli/dist/index.js --help
The full development workflow, stack, end-to-end smoke tests, and teardown live in docs/development.md.
The macOS tray app lives in the sibling repo ../agentbox-tray. When you have it checked out next to this repo, these scripts build and run your local dev build (ad-hoc signed, at ../agentbox-tray/AgentBoxTray.app) — separate from the notarized copy agentbox install tray puts in /Applications:
pnpm tray:dev # rebuild the dev .app and relaunch it (the one you'll use most)
pnpm tray:build # just rebuild (scripts/make-app.sh)
pnpm tray:start # launch the dev build
pnpm tray:stop # quit any running instance
pnpm tray:restart # quit + relaunch the dev build
Note:
agentbox app start|restarttargets the installed/Applicationscopy, not this dev build. Use thepnpm tray:*scripts while iterating on the tray here; runagentbox install trayto refresh/Applicationsfrom the current CLI build.
AgentBox's provider surface is open — you can run agents on your own cloud/infra by shipping a provider plugin (its own npm package built on @madarco/agentbox-provider-sdk), with no changes to AgentBox. Build and test against the bundled example provider locally: