How to run a sfcompute sandbox (via web, CLI, API, or AI agent)

Create a sfcompute sandbox in one command, with no sfcompute account or API key. Or use the dashboard, an AI agent, the API, or the SDK. Median burst TTI 621 ms in our Nov 20, 2026 benchmark.

David Tice

Head of Product ·

sfcompute (formerly Give Me A Node) provides fast microVM sandboxes served from a per-region warm pool.

You don't need a sfcompute account, provider SDK, or API key to use it. ComputeSDK runs sfcompute sandboxes on its managed sfcompute account and bills them from your ComputeSDK credit. Sign up once, and you can create a sfcompute sandbox from the dashboard, your terminal, an AI agent, a REST call, or a few lines of TypeScript. If you already have a sfcompute account, you can bring your own key too.

  • Dashboard: open Sandboxes → New sandbox and pick sfcompute.
  • CLI: run compute new givemeanode.
  • MCP: connect Claude, ChatGPT, or another agent to https://platform.computesdk.com/mcp.
  • REST API: call POST /api/v1/sandboxes from any language.
  • SDK: import { compute } from 'computesdk' in a TypeScript app.

How sfcompute performs

ComputeSDK benchmarks sfcompute alongside every other sandbox provider on the same hardware and schedule. Its current results, as of November 20, 2026:

See every result on the sfcompute provider page. Browse the burst TTI, DAX and reliability leaderboards.

Popular comparisons: sfcompute vs Agent37, sfcompute vs Archil, sfcompute vs Arker.

Before you start

Create an account at platform.computesdk.com with Google, GitHub, or email. Your account comes with an organization, and every sandbox you create belongs to it.

Sandboxes on ComputeSDK's managed sfcompute account are billed per second from your prepaid credit, which you can add under Settings → Billing. You only pay sfcompute directly if you bring your own key.

1. Create a sandbox in the dashboard

  1. Sign in to platform.computesdk.com and open Sandboxes in the sidebar.
  2. Click New sandbox.
  3. Under Size, pick how much CPU and memory you want.
  4. Under Routing, pick sfcompute.
  5. Click Create sandbox.

The New sandbox form on the ComputeSDK dashboard, with Size and Routing selected (shown with Vercel; the steps are the same for sfcompute)

The new sandbox appears in the Sandboxes list, and you can destroy it from there when you're done.

These sizes were available on the managed sfcompute account when we wrote this. The dashboard always shows the current list and the price for each one.

  • small: 1 vCPU · 2 GB
  • large: 4 vCPU · 8 GB
  • xlarge: 8 vCPU · 32 GB
  • 2xlarge: 16 vCPU · 64 GB

2. Create a sandbox from the CLI

Install the CLI and create a sfcompute sandbox:

npm install -g @computesdk/cli
compute new givemeanode

If you aren't signed in yet, compute new opens the browser sign-in first (you can also run compute login yourself). The new sandbox becomes the current sandbox for your directory, so the next commands don't need its ID:

compute exec echo hello   # run a command
compute list              # see your sandboxes
compute destroy           # stop it and stop billing

compute new creates a sandbox and prints how to use it (shown with Vercel; the steps are the same for sfcompute)

Run compute new givemeanode . to also copy your current project into the sandbox at /app.

3. Let an AI agent create it over MCP

ComputeSDK has a remote MCP server, so an AI agent can create and use sandboxes for you. Connect it to your agent:

  • Claude (web and desktop): go to Settings → Connectors → Add custom connector and enter https://platform.computesdk.com/mcp, or add ComputeSDK Router from the connectors directory.
  • Claude Code: run claude mcp add --transport http computesdk https://platform.computesdk.com/mcp.
  • ChatGPT: install the ComputeSDK Router app from the ChatGPT apps directory.
  • Any other MCP client: point it at https://platform.computesdk.com/mcp.

The first time the agent uses a tool, a ComputeSDK sign-in opens in your browser. Sign in with OAuth, choose the organization the agent should use, and approve the permissions. That's it. Now ask for what you want:

Create a sfcompute sandbox, run node -v in it, and destroy it when you're done.

The agent creates the sandbox, runs commands, reads and writes files, starts servers, and shares a public preview URL for a port, all through ComputeSDK. Nothing runs on your computer. To disconnect, remove the app under Settings → Connected Apps.

4. Create a sandbox with the REST API

For direct calls from any language, use an organization API key:

  1. Sign in to the platform and open Settings → API Keys.
  2. Create a key and copy it. It is shown only once.
  3. Export it in your shell:
export COMPUTE_API_KEY="your_org_api_key"

Create a sfcompute sandbox:

curl https://platform.computesdk.com/api/v1/sandboxes \
  -H "Authorization: Bearer $COMPUTE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"only":["givemeanode"],"size":"small"}'

only limits this create to sfcompute. The response's sandbox.id is what you use in the next calls. Run a command, then destroy the sandbox:

curl https://platform.computesdk.com/api/v1/sandboxes/$SANDBOX_ID/commands \
  -H "Authorization: Bearer $COMPUTE_API_KEY" \
  -H 'Accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{"command":"echo hello"}'
 
curl -X DELETE https://platform.computesdk.com/api/v1/sandboxes/$SANDBOX_ID \
  -H "Authorization: Bearer $COMPUTE_API_KEY"

Creating a sandbox and running a command with curl (shown with Vercel; the steps are the same for sfcompute)

The same API also handles files, background processes, and preview URLs. See the API reference.

5. Create a sandbox with the SDK

In a TypeScript or JavaScript app, install the SDK and use the same API key:

npm install computesdk
export COMPUTE_API_KEY="your_org_api_key"
import { compute } from 'computesdk';
 
const sandbox = await compute.instances.create({
  // Follows your routing under Settings → Sandboxes; pick sfcompute there.
  size: 'small',
});
try {
  const result = await sandbox.runCommand('echo hello');
  console.log(result.stdout);
} finally {
  await sandbox.destroy();
}

Importing computesdk is all it takes: the SDK reads COMPUTE_API_KEY and talks to the platform, so there is no sfcompute package or sfcompute credential in your app. compute.instances.create() follows your organization's saved routing, so pick sfcompute under Settings → Sandboxes to send sandboxes there. The SDK can't pin a single create to ComputeSDK's managed sfcompute account; only the routing setting does that. If you've connected your own sfcompute key, providerOrder: ['givemeanode'] pins one create to that key, with no fallback.

Creating a sandbox with the computesdk package

Bring your own key: try it first, or as a fallback

If you already have a sfcompute account, you can connect its key to ComputeSDK and decide how it is used alongside the managed account. Sandboxes on your own key are billed by sfcompute, not from your ComputeSDK credit.

  1. Add your key under Settings → BYOK.
  2. Open Settings → Sandboxes and set Use BYOK accounts:
  • First: try your own keys first, then ComputeSDK's managed accounts.
  • Fallback: use managed accounts first, then fall back to your own keys.
  • Only: use only your own keys.
  • Off: use only managed accounts.

The Use BYOK accounts setting under Settings → Sandboxes

The setting applies everywhere: the dashboard, CLI, MCP, API, and SDK. You can still override it for a single create, for example compute new givemeanode --byok to use your key or compute new givemeanode --managed to use the managed account. From the API, set it with PATCH /api/v1/sandboxes/routing and {"byok":"first"}, or pass byok on a single create.

Next steps

Frequently asked questions

Do I need a sfcompute account to run a sfcompute sandbox?

No. ComputeSDK runs sfcompute sandboxes on its managed sfcompute account and bills them per second from your ComputeSDK credit. You can also connect your own sfcompute key.

How do I create a sfcompute sandbox from the terminal?

Run compute new givemeanode. The first time, the CLI opens your browser so you can sign in to ComputeSDK. Then run commands with compute exec and clean up with compute destroy.

Can an AI agent create sfcompute sandboxes?

Yes. Connect Claude, ChatGPT, or another MCP client to https://platform.computesdk.com/mcp and sign in with OAuth. The agent can then create a sfcompute sandbox, run commands, edit files, and destroy it.

Can I use my own sfcompute key with ComputeSDK?

Yes. Add it under Settings → BYOK, then set Use BYOK accounts under Settings → Sandboxes to First to try your key before managed accounts, or Fallback to use managed accounts first and your key as a backup.

Get new posts by email

Questions or thoughts on this post?

Join the conversation on X