Run your coding agent across clouds.

Run code in Sandbox, call models through Router, and see what your agent changed.

Explore the examples

Give each agent its own machine.

Run commands, edit files and inspect the changes alongside each step your agent took.

SDK reference
sandboxes/fix-a-test.mts
import { writeFile } from "node:fs/promises";
import { Sandbox } from "@tangle-network/sandbox";

const client = new Sandbox({
  apiKey: process.env.TANGLE_API_KEY!,
  baseUrl: "https://sandbox.tangle.tools",
});

const box = await client.create({
  git: { url: "https://github.com/tangle-network/sandbox-demo" },
  backend: { type: "claude-code" }, // or "codex", "opencode", "pi"
});
try {
  const run = await box.prompt("`npm test` fails. Find the cause and fix it.");
  if (!run.success) throw new Error(run.error);

  // Check the result yourself.
  const tests = await box.exec("npm test");
  if (tests.exitCode !== 0) throw new Error("The tests still fail.");

  await writeFile("fix.patch", (await box.exec("git diff")).stdout);
  console.log(run.usage, run.costUsd); // metered per turn
} finally {
  await box.delete();
}

First recorded step

Change models without moving your agent.

Point your OpenAI-compatible client at Tangle Router. Choose the model with each request, wherever your agent runs.

Explore models

Choose your coding agent.

Configure with the CLI or API

  • Amp
  • NanoClaw
  • Nanocode
  • ACP
  • Cursor
  • Grok
CLI and API setup

One key. One bill.

Compute, inference and observability, on one balance.

Free

$0

No included credit

  • 1 concurrent sandbox
  • 3 snapshots per sandbox
  • 100 GiB egress per account each month, refused beyond it, never charged

Team

$99 / month

Your $99 comes back as credit each month

  • Unlimited sandboxes
  • 25 snapshots per sandbox
  • 2 TB egress per sandbox each month, then $0.04/GB