Run Muse Code in a CoreWeave sandbox

Run Muse Code inside a CoreWeave sandbox to edit files and execute commands in a remote workspace. This guide uses the Sandbox software development kit (SDK) to install the command-line interface (CLI) and clone a repository. You then run a task without an interactive terminal and retrieve the result before you stop the sandbox. The agent process and workspace run on CoreWeave, and model requests go to Meta.

CoreWeave Serverless sandboxes are in public preview.

Prerequisites

Before you begin, you need the following:

A W&B API key. These examples select W&B authentication. For other credentials, see Choose a credential.
A Meta API key with access to Muse Code.
A public repository URL the sandbox can clone. Private repositories require Git credentials inside the sandbox.
Python 3.11 or later with uv, or Node.js 22 or later with npm.

Load your credentials from your secret manager into your local terminal environment. Replace [WANDB-API-KEY] with your W&B API key and [META-API-KEY] with your Meta API key:

export WANDB_API_KEY="[WANDB-API-KEY]"
export META_API_KEY="[META-API-KEY]"

The script passes the Meta key over standard input so it doesn’t appear in command arguments or sandbox configuration. For a shared team credential injected as an environment variable at sandbox creation, see W&B secrets.

Install the Sandbox client

Choose a language and prepare a local project:

Python
TypeScript

mkdir muse-sandbox
cd muse-sandbox
uv init --bare --python 3.11
uv venv --python 3.11
source .venv/bin/activate
uv pip install 'cwsandbox[wandb]>=1.14.2'

mkdir muse-sandbox
cd muse-sandbox
npm init -y
npm install @coreweave/cwsandbox@0.5.0-beta.0 tsx

Run a task in the sandbox

Save the script for your language using the filename shown. Each script creates a serverless sandbox with a 30-minute maximum lifetime and performs these steps:

Installs Muse Code with Meta’s installer.
Clones your repository into the /workspace/project directory.
Runs muse exec to build and test a sparkline CLI that renders numbers as a small chart.
Runs the generated CLI independently, checks its output, and saves the sparkline.mjs file locally.
Stops the sandbox in a finally block, including when setup or execution fails.

These examples were tested with Muse Code 1.3.0. The installer can install a newer version, so each script runs muse --version after installation. The example uses --yolo to disable Muse Code’s approval prompts and operating system (OS) sandbox and trust the workspace for this run. CoreWeave supplies the outer sandbox. Muse can access files, credentials, and network destinations available inside that sandbox. Use a repository you trust and provide only the credentials the task needs. For more information, see Muse Code permissions.

Python
TypeScript

run_muse.py

import os
import sys
from pathlib import Path

from cwsandbox import AuthStrategy, Sandbox

if len(sys.argv) != 2:
    raise SystemExit("Usage: python run_muse.py [REPOSITORY-URL]")
meta_api_key = os.environ["META_API_KEY"]

sandbox = Sandbox.run(
    auth=AuthStrategy.WANDB,
    container_image="node:22-bookworm",
    resources={"cpu": "2", "memory": "4Gi"},
    max_lifetime_seconds=1800,
    tags=["muse-code"],
)
try:
    sandbox.wait()
    commands = [
        ["bash", "-o", "pipefail", "-ec", "curl -fsSL https://dev.meta.ai/install.sh | bash"],
        ["bash", "-ec", '"$HOME/.local/bin/muse" --version'],
        ["git", "clone", "--", sys.argv[1], "/workspace/project"],
    ]
    for command in commands:
        result = sandbox.exec(command, timeout_seconds=600, check=True).result()
        print(result.stdout, end="")

    agent = sandbox.exec(
        [
            "bash", "-ec",
            'IFS= read -r META_API_KEY; export META_API_KEY; '
            'exec "$HOME/.local/bin/muse" exec --yolo "$1"',
            "bash",
            "Create sparkline.mjs, a dependency-free Node.js CLI that converts its "
            "numeric arguments to a sparkline using ▁▂▃▄▅▆▇█. Scale from the minimum "
            "to the maximum and round to the nearest bar index. "
            "Running node sparkline.mjs 2 4 8 4 2 must print ▁▃█▃▁ followed by "
            "a newline. Run that command to test it.",
        ],
        cwd="/workspace/project",
        stdin=True,
        timeout_seconds=600,
    )
    # Keep stdin open until Muse finishes to avoid aborting a quiet request.
    agent.stdin.writeline(meta_api_key).result()
    result = agent.result()
    print(result.stdout, end="")
    print(result.stderr, end="", file=sys.stderr)
    if result.returncode != 0:
        raise SystemExit(result.returncode)

    chart = sandbox.exec(
        ["node", "sparkline.mjs", "2", "4", "8", "4", "2"],
        cwd="/workspace/project", check=True,
    ).result()
    if chart.stdout != "▁▃█▃▁\n":
        raise RuntimeError(f"Unexpected sparkline: {chart.stdout!r}")
    print(chart.stdout, end="")
    source = sandbox.exec(
        ["cat", "/workspace/project/sparkline.mjs"], check=True
    ).result()
    Path("sparkline.mjs").write_text(source.stdout, encoding="utf-8")
finally:
    sandbox.stop().result()

run_muse.mts

import { writeFile } from "node:fs/promises";
import { createSandboxClientFromEnv } from "@coreweave/cwsandbox/wandb";

const repository = process.argv[2];
if (!repository) throw new Error("Pass a repository URL.");
const metaApiKey = process.env.META_API_KEY;
if (!metaApiKey) throw new Error("Set META_API_KEY.");

const client = createSandboxClientFromEnv();
const sandbox = await client.create({
  containerImage: "node:22-bookworm",
  resources: { cpu: "2", memory: "4Gi" },
  maxLifetimeSeconds: 1800,
  waitUntilRunning: false,
  tags: ["muse-code"],
});
try {
  await sandbox.wait();
  const commands = [
    ["bash", "-o", "pipefail", "-ec", "curl -fsSL https://dev.meta.ai/install.sh | bash"],
    ["bash", "-ec", '"$HOME/.local/bin/muse" --version'],
    ["git", "clone", "--", repository, "/workspace/project"],
  ];
  for (const command of commands) {
    const result = await sandbox.commands.run(command, { timeoutMs: 600_000, check: true });
    process.stdout.write(result.stdout);
  }

  const agent = await sandbox.commands.start(
    [
      "bash", "-ec",
      'IFS= read -r META_API_KEY; export META_API_KEY; ' +
        'exec "$HOME/.local/bin/muse" exec --yolo "$1"',
      "bash",
      "Create sparkline.mjs, a dependency-free Node.js CLI that converts its " +
        "numeric arguments to a sparkline using ▁▂▃▄▅▆▇█. Scale from the minimum " +
        "to the maximum and round to the nearest bar index. " +
        "Running node sparkline.mjs 2 4 8 4 2 must print ▁▃█▃▁ followed by " +
        "a newline. Run that command to test it.",
    ],
    {
      cwd: "/workspace/project",
      stdin: true,
      timeoutMs: 600_000,
    },
  );
  // Keep stdin open until Muse finishes to avoid aborting a quiet request.
  await agent.stdin.write(metaApiKey + "\n");
  const result = await agent.wait();
  process.stdout.write(result.stdout);
  process.stderr.write(result.stderr);
  if (!result.ok) throw new Error(`Muse Code exited with code ${result.exitCode}.`);

  const chart = await sandbox.commands.run(
    ["node", "sparkline.mjs", "2", "4", "8", "4", "2"],
    { cwd: "/workspace/project", check: true },
  );
  if (chart.stdout !== "▁▃█▃▁\n") {
    throw new Error(`Unexpected sparkline: ${JSON.stringify(chart.stdout)}`);
  }
  process.stdout.write(chart.stdout);
  const source = await sandbox.commands.run(
    ["cat", "/workspace/project/sparkline.mjs"], { check: true },
  );
  await writeFile("sparkline.mjs", source.stdout, "utf8");
} finally {
  await sandbox.stop();
}

In your local project directory, replace [REPOSITORY-URL] with your public repository URL, then run the script:

Python
TypeScript

python run_muse.py [REPOSITORY-URL]

npx tsx run_muse.mts [REPOSITORY-URL]

After the installation and agent output, the script checks and prints the sparkline:

▁▃█▃▁

The script saves the generated sparkline.mjs file in your local project directory, then stops the sandbox. If the file already exists locally, the script overwrites it. The output check runs independently of Muse’s own test and verifies this example’s input. For a larger task, replace it with tests for your requirements. These examples don’t configure persistent storage. Copy the files you need out of the sandbox before the finally block runs. See file operations and file system snapshots.

Troubleshoot

Use these checks to resolve common issues:

If sandbox creation fails, check your W&B key and authentication settings.
If Muse Code reports an authentication error, check META_API_KEY and your Meta account setup. The sandbox credential doesn’t authenticate model requests.
If installation, cloning, or model requests fail, check outbound access to Meta and your Git host. These examples use serverless placement. To use your own CoreWeave Kubernetes Service (CKS) cluster, switch to a CoreWeave API access token and the client settings in Configure CKS placement and policy. Confirm that the runner’s policy grants egress to those destinations.
If a larger task times out, adjust the command timeout and sandbox lifetime before running it. The 30-minute lifetime includes startup and installation. See command timeouts and sandbox lifecycle.

Next steps

For more information, see these guides:

Interactive shells and TTY covers terminal access for interactive agents.
Run agents on CoreWeave sandboxes compares agent integrations and workspace options.
Meta’s sandboxed execution cookbook demonstrates a reproduce, fix, and verify workflow with a custom tool loop in Docker.
Muse Code documentation covers agent configuration and other CLI workflows.

​Prerequisites

​Install the Sandbox client

​Run a task in the sandbox

​Troubleshoot

​Next steps

Prerequisites

Install the Sandbox client

Run a task in the sandbox

Troubleshoot

Next steps