Skip to main content
SmolVM lets you run coding agents and agent tools like Claude, Codex, OpenCode, OpenClaw, Hermes, and Pi inside an isolated sandbox. The agent gets a full development environment — git credentials, dev tools, terminal access — but nothing it does can affect your host machine. No more pressing “accept changes” every few seconds. Let the agent work freely in its own computer.
Want to keep Pi and its model credentials on your machine while its coding tools run in the cloud? Follow Run Pi coding agent in the cloud.

​
Start a coding agent

Each command creates a sandbox and prepares the selected agent. Most presets forward supported credentials and configuration from your machine when available. OpenClaw starts with fresh configuration and only receives supported credential variables from the shell that starts SmolVM. Presets with a matching pre-built image skip installation after downloading that image. Download time depends on your connection. OpenClaw and OpenCode currently install inside each new sandbox. See Published images for details.

​
Work with OpenClaw

OpenClaw includes a browser dashboard. Follow these steps to create a sandbox, find it later, and open the dashboard.
1

Create an OpenClaw sandbox

Create a named sandbox without opening its terminal session:
SmolVM installs OpenClaw 2026.9.1 on Node.js 24.15.0 or newer after the sandbox starts, so creating each new sandbox can take several minutes. SmolVM shows each installation step while you wait. The OpenClaw preset supports Ubuntu sandboxes only.The sandbox does not inherit ~/.openclaw/openclaw.json, ~/.openclaw/.env, or other OpenClaw state from your machine. Set a supported credential variable before starting SmolVM, or run openclaw onboard inside the sandbox.
2

Find a running OpenClaw sandbox

List your running OpenClaw sandboxes when you need the name:
3

Check every state

Include stopped, paused, and errored OpenClaw sandboxes with --all, narrow to one state with --status, or emit machine-readable output with --json:
4

Check for older sandboxes

The filtered list includes sandboxes that current SmolVM releases created with the OpenClaw preset. To look for an older or manually prepared sandbox, view the complete inventory:
5

Open the dashboard

Use the sandbox name from the list:
SmolVM starts the OpenClaw dashboard service when needed, creates a private connection available only on your machine, and opens a one-time link.
In SmolVM v0.0.31, smolvm openclaw open-ui replaces smolvm openclaw open. Update existing scripts: the old command is no longer accepted.
open-ui accepts three flags:
  • --host-port PORT — pin the localhost port that forwards to the dashboard. When omitted, SmolVM chooses a free port.
  • --no-browser — print the one-time link instead of launching a browser. Useful on remote or headless machines.
  • --json — emit a machine-readable envelope with the sandbox name, dashboard URL, chosen host port, and cleanup command.
Treat the link as a credential. Close the local connection with the exact smolvm sandbox port close command printed by open-ui. Updating SmolVM leaves OpenClaw inside existing sandboxes unchanged. Before replacing an older sandbox, save a snapshot with sandbox snapshots. See Coding-agent preset environment variables for the credentials that you can explicitly pass to a fresh OpenClaw sandbox.

​
OpenCode credentials

OpenCode works with multiple model providers, so the opencode preset forwards the common provider keys from your host environment: ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, GEMINI_API_KEY, OPENROUTER_API_KEY, and the AWS credential variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, AWS_REGION). The preset also copies your OpenCode configuration into the sandbox:
  • ~/.config/opencode — your OpenCode settings
  • ~/.local/share/opencode/auth.json — stored provider logins, copied with owner-only permissions
If none of these are present on your host, start the sandbox anyway and run opencode auth login inside it.

​
What you get

Each coding agent sandbox comes with:
  • Isolated environment — the agent runs in its own VM, separate from your host
  • Git credentials — pre-configured so the agent can clone, commit, and push
  • Dev tools — common development tooling ready to use
  • Terminal access — full shell access for multi-step workflows

​
Share folders with the sandbox

You can share folders from your machine so the coding agent can see your existing code. By default, shared folders are read-only — the agent can read your files but cannot modify the originals.
The agent sees your project files inside the sandbox at /workspace. To let the agent write changes back to your machine, add --writable-mounts:
With --writable-mounts, the agent can modify and delete files in the shared folder. Only enable this when you trust the code the agent will run.
See the host mounts guide for more options like sharing multiple folders and custom mount paths.
Last modified on September 11, 2026