Cloud Sandbox Extension Examples

These examples are for manual verification of the cloud sandbox backends that live under agents.extensions.sandbox.

They intentionally keep the flow simple:

Build a tiny manifest in memory.
Create a SandboxAgent that inspects that workspace through one shell tool.
Run the agent against E2B, Modal, Daytona, Cloudflare, Runloop, Blaxel, or Vercel.

All of these examples require OPENAI_API_KEY, because they call the model through the normal Runner path. Each cloud backend also needs its own provider credentials.

E2B

Setup

Install the repo extra:

uv sync --extra e2b

Create an E2B account, create an API key, and export it as E2B_API_KEY. The official setup docs are:

Export the required environment variables:

export OPENAI_API_KEY=...
export E2B_API_KEY=...

Run

uv run python examples/sandbox/extensions/e2b_runner.py --stream

Useful flags:

--sandbox-type e2b_code_interpreter
--template <template-name>
--timeout 300
--pause-on-exit

The example defaults to e2b, which provides a bash-style interface. Use e2b_code_interpreter for a Jupyter-style interface.

Modal

If you want the same explicit session lifecycle shown in examples/sandbox/basic.py, that example now accepts --backend modal and reuses the same streamed tool-output flow:

uv run python examples/sandbox/basic.py \
  --backend modal

The dedicated script below stays as the smaller extension-specific example.

Setup

Install the repo extra:

uv sync --extra modal

Authenticate Modal with either CLI token setup or environment variables. The official references are:

If you want to configure credentials directly from the CLI:

uv run modal token set --token-id <token-id> --token-secret <token-secret>

Or export environment variables for the current shell:

export OPENAI_API_KEY=...
export MODAL_TOKEN_ID=...
export MODAL_TOKEN_SECRET=...

Run

uv run python examples/sandbox/extensions/modal_runner.py \
  --app-name openai-agents-python-sandbox-example \
  --stream

Useful flags:

--workspace-persistence tar
--workspace-persistence snapshot_filesystem
--workspace-persistence snapshot_directory
--sandbox-create-timeout-s 60
--native-cloud-bucket-secret-name my-modal-secret

app_name is required by ModalSandboxClientOptions, so the example makes it an explicit CLI flag instead of hiding it.

Modal sandboxes also support native cloud bucket mounts through ModalCloudBucketMountStrategy on S3Mount, R2Mount, and HMAC-authenticated GCSMount.

For native cloud bucket testing, you can either export raw credential environment variables or pass --native-cloud-bucket-secret-name to reuse an existing named Modal Secret instead.

Cloudflare

Setup

Install the repo extra:

uv sync --extra cloudflare

Export the required environment variables:

export OPENAI_API_KEY=...
export CLOUDFLARE_SANDBOX_WORKER_URL=...

If your Cloudflare Sandbox Service worker requires bearer auth, also export:

export CLOUDFLARE_SANDBOX_API_KEY=...

Run

uv run python examples/sandbox/extensions/cloudflare_runner.py --stream

Useful flags:

--stream -- stream model output to the terminal.
--demo pty -- run a PTY demo (interactive Python session with tty=true).
--skip-snapshot-check -- skip the stop/resume snapshot round-trip verification.
--native-cloud-bucket-name <bucket> -- mount an R2/S3 bucket via CloudflareBucketMountStrategy.
--native-cloud-bucket-endpoint-url <url> -- optional S3 endpoint URL.
--api-key <key> -- bearer token for the worker (or set CLOUDFLARE_SANDBOX_API_KEY).

Cloudflare sandboxes support native cloud bucket mounts through CloudflareBucketMountStrategy on S3Mount, R2Mount, and HMAC-authenticated GCSMount.

What to expect

Each script asks the model to inspect a small workspace and summarize it. A successful run should:

Start the chosen cloud sandbox backend.
Materialize the manifest into the sandbox workspace.
Call the shell tool at least once.
Print either streamed text or a final short answer about the workspace.

These examples are not live-validated in CI because they depend on external cloud credentials, but they are shaped so contributors can verify backend behavior locally with one command per provider.

Vercel

Setup

Install the repo extra:

uv sync --extra vercel

Export the required environment variables:

export OPENAI_API_KEY=...
export VERCEL_OIDC_TOKEN=...

Or use explicit token and scope variables:

export OPENAI_API_KEY=...
export VERCEL_TOKEN=...
export VERCEL_PROJECT_ID=...
export VERCEL_TEAM_ID=...

Run

uv run python examples/sandbox/extensions/vercel_runner.py --stream

Useful flags:

--demo pty
--demo port
--demo backend-checks
--workspace-persistence tar
--workspace-persistence snapshot
--runtime node22
--timeout-ms 120000

The default Vercel run mirrors the other cloud runners and stays focused on the standard agent flow. Use --demo for backend-specific checks such as PTY, resume verification, and exposed-port validation.

Daytona

Setup

Install the repo extra:

uv sync --extra daytona

Export the required environment variables:

export OPENAI_API_KEY=...
export DAYTONA_API_KEY=...

Run

uv run python examples/sandbox/extensions/daytona/daytona_runner.py --stream

Runloop

Setup

Install the repo extra:

uv sync --extra runloop

Sign up for Runloop, no credit card required and $50 in credits @ platform.runloop.ai. Export the required environment variables:

export OPENAI_API_KEY=...
export RUNLOOP_API_KEY=...

Run

uv run python examples/sandbox/extensions/runloop/runner.py --stream

Useful flags:

--blueprint-name <name>
--pause-on-exit
--root

Runloop-specific SDK features are also available directly on RunloopSandboxClientOptions and RunloopSandboxClient.platform. Example:

from agents.extensions.sandbox.runloop import (
    RunloopAfterIdle,
    RunloopGatewaySpec,
    RunloopLaunchParameters,
    RunloopMcpSpec,
    RunloopSandboxClient,
    RunloopSandboxClientOptions,
    RunloopTunnelConfig,
)

client = RunloopSandboxClient()
sandbox = await client.create(
    options=RunloopSandboxClientOptions(
        blueprint_name="python-3-12",
        launch_parameters=RunloopLaunchParameters(
            network_policy_id="np_123",
            resource_size_request="MEDIUM",
            after_idle=RunloopAfterIdle(idle_time_seconds=300, on_idle="suspend"),
        ),
        tunnel=RunloopTunnelConfig(auth_mode="authenticated"),
        gateways={
            "OPENAI_GATEWAY": RunloopGatewaySpec(
                gateway="openai",
                secret="OPENAI_GATEWAY_SECRET",
            )
        },
        mcp={
            "GITHUB_MCP": RunloopMcpSpec(
                mcp_config="github-readonly",
                secret="GITHUB_MCP_SECRET",
            )
        },
        managed_secrets={"OPENAI_API_KEY": "..."},
        metadata={"team": "agents"},
    )
)

public_blueprints = await client.platform.blueprints.list_public()
public_benchmarks = await client.platform.benchmarks.list_public()

managed_secrets are stored as Runloop account secrets and only secret references are persisted in session state. The platform facade also exposes Runloop-native helpers for blueprints, benchmarks, secrets, network policies, and axons.

If you enable --root, Runloop launches the devbox with launch_parameters.user_parameters={"username":"root","uid":0}. In that mode, the default home and working directory become /root, so the example also uses /root as its manifest workspace root. If you configure root launch in your own code, either rely on that root-mode default or explicitly choose a manifest.root under /root.

Blaxel

Setup

Install the repo extra:

uv sync --extra blaxel

Create a Blaxel account and get an API key. The official docs are:

Export the required environment variables:

export OPENAI_API_KEY=...
export BL_API_KEY=...
export BL_WORKSPACE=...

Run

uv run python examples/sandbox/extensions/blaxel_runner.py --stream

Useful flags:

--image blaxel/py-app
--region us-pdx-1
--memory 4096
--ttl 1h
--pause-on-exit
--skip-snapshot-check

The runner also includes standalone demos for individual features. Pass --demo <name> to run one:

pty -- agent-driven interactive Python session via PTY
drive -- Blaxel Drive mount (persistent storage, requires --drive-name)

Blaxel sandboxes support cloud bucket mounts (S3, R2, GCS) through BlaxelCloudBucketMountStrategy and persistent drive mounts through BlaxelDriveMountStrategy. See the Blaxel Drive docs for details.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Cloud Sandbox Extension Examples

E2B

Setup

Run

Modal

Setup

Run

Cloudflare

Setup

Run

What to expect

Vercel

Setup

Run

Daytona

Setup

Run

Runloop

Setup

Run

Blaxel

Setup

Run

FilesExpand file tree

README.md

Latest commit

History

README.md

File metadata and controls

Cloud Sandbox Extension Examples

E2B

Setup

Run

Modal

Setup

Run

Cloudflare

Setup

Run

What to expect

Vercel

Setup

Run

Daytona

Setup

Run

Runloop

Setup

Run

Blaxel

Setup

Run