Skip to main content
Connect Claude Managed Agents to a worker running in a CoreWeave sandbox. Anthropic manages the agent loop and conversation. The worker executes tools and returns their results to Anthropic. This integration uses a self-hosted environment and is separate from the Claude Code CLI and Remote Control.
CoreWeave Serverless sandboxes are in public preview.
Claude Managed Agents is also in beta. Its API requires the managed-agents-2026-04-01 beta header. The Anthropic SDK used in this guide adds it automatically. See Anthropic beta access.

Prerequisites

Before you begin, you need the following:
  • A W&B API key. These examples use W&B authentication. For other credentials, see Choose a credential.
  • Claude Managed Agents access in your Anthropic workspace and a Console API key for the client that creates sessions.
  • An existing agent configured with agent_toolset_20260401. Follow Anthropic’s Managed Agents quick start to create one and record its ID.
  • For the SDK examples, either Python 3.11 or later with uv, or Node.js 22 or later.
Export your W&B API key in the terminal where you run this guide. Unset any CoreWeave token so cws-agent selects W&B authentication:
W&B users don’t need the SANDBOX_USER Identity and Access Management (IAM) action. That permission applies only when authenticating with a CoreWeave API access token.

Create an environment

In the Claude Console, create a Self-hosted environment. Open it and generate an environment key. Record the environment ID and store the key securely. See Anthropic’s environment setup. The environment key authenticates workers to this environment. The Console API key creates sessions from your client. Keep the two credentials separate. For the verification task, use an environment with only the worker created in this guide. That prevents another worker from claiming the test session. With the environment ready, choose either cws-agent or the Sandbox SDK to start its worker, then run the verification task.

Quick start with cws-agent

Follow the cws-agent installation instructions. The tool configures a snapshot volume to save and restore your workspace with file system snapshots. Replace [ENVIRONMENT-KEY], [ENVIRONMENT-ID], and [SANDBOX-NAME] with your environment key, environment ID, and a cws-agent session name for the sandbox. For the session name, use 1 to 40 lowercase letters, digits, or hyphens, starting with a letter or digit:
Launch starts one worker in /workspace/claude/0 and returns to your shell. The tool passes the environment key into the sandbox. For platform-managed secret references, see Use a secret store. To view the worker’s terminal, run:
Detach with Ctrl-b, then d. Continue to Run and verify a task. Send tasks through the Managed Agents API. The cws-agent run command doesn’t drive Managed Agents conversations.

Set up with the Sandbox SDK

This alternative starts Anthropic’s ant worker as the sandbox’s main process. It doesn’t require cws-agent or configure snapshots. Run Python snippets in the virtual environment created in this guide. Save TypeScript snippets as .mts files in the project where you install the client, then run them with npx tsx [FILENAME].mts.

Configure credentials and install the client

Export the environment key and ID from the Console in the terminal where you run the script:
Use Python 3.11 or later and uv:

Start the worker

Save the script for your language using the filename shown. The script installs the ant CLI in a Linux image with Bash, starts one worker, and prints the sandbox ID. The client reads ANTHROPIC_ENVIRONMENT_KEY from your local environment and passes its value in the sandbox request to set the worker’s environment variable.
start_claude_worker.py
Run the script:
The script waits for startup. In Python, wait() can also return if the main process has already completed. A printed sandbox ID doesn’t confirm that the worker is authenticated or polling. Before starting a task, inspect its status and recent logs. Replace [SANDBOX-ID] with the printed ID:
The Python client also reports per-container state, exit codes, and restart counts. The TypeScript client doesn’t expose those details yet. Rerun this check to fetch newer logs. This worker polls over outbound HTTPS. It doesn’t require an inbound service. Each session uses the same sandbox filesystem, so this example doesn’t provide a fresh sandbox per session. For that architecture, see Anthropic’s self-hosted sandbox integration guide.

Optional: Use a secret store

If your administrator has configured a secret store for your organization, you can pass a reference instead of the environment key value. Store the key there and obtain the verified store and entry names from your administrator. There is no universal store name.
Import Secret from cwsandbox, remove ANTHROPIC_ENVIRONMENT_KEY from environment_variables, and add secrets=[Secret(store="[SECRET-STORE]", name="[SECRET-NAME]", env_var="ANTHROPIC_ENVIRONMENT_KEY")] to Sandbox.run().
Replace both placeholders with the verified names. The platform resolves the reference and sets the worker’s environment variable.

Run and verify a task

Run the session client on your own machine for either setup path. Install the Anthropic SDK for your language:
Replace [ANTHROPIC-API-KEY] with your Console API key, [AGENT-ID] with your existing agent ID, and [ENVIRONMENT-ID] with the environment connected to your worker:
Save the verification script for your language using the filename shown. It asks the agent to write a unique, non-secret value in its working directory. Self-hosted tool execution produces temporary idle events while the worker handles allowed calls. The script waits through those events and stops when the turn ends or another action is required. Inspect the printed stop reason before retrieving the file.
verify_claude_worker.py
Run it and inspect the events:
If the script stops with requires_action, inspect the referenced tool events. Calls with evaluated_permission: "ask" need Anthropic’s tool-confirmation workflow. The worker handles allowed calls. If they stall, inspect its logs. Keep the session ID to continue that session rather than creating another one. After the task completes, read the file from the sandbox with the command for your setup. Replace [SANDBOX-NAME] or [SANDBOX-ID] with the workspace name or printed sandbox ID:
For Python, reactivate the virtual environment where you installed cwsandbox if needed. For TypeScript, save the SDK snippet as an .mts file and run it with npx tsx. The file must match the value printed by the client. This ties the agent’s tool execution to the specific CoreWeave sandbox.

Keep results and stop

Wait for active tasks to finish and copy any results you need out of the sandbox. Then stop it using the command for your setup:
down snapshots the workspace before stopping. If capture fails, check cws-agent status [SANDBOX-NAME] and resolve the failure before retrying. If you can discard unsaved changes, use down --no-snapshot.
The sandbox’s lifetime can terminate a task in progress. Ending a Managed Agents session doesn’t stop this always-on worker. Stopping or restoring the sandbox also doesn’t delete or restore Anthropic’s conversation history.

Troubleshoot

Use these checks to resolve common issues:
  • If the session waits for a worker, check the environment ID, the worker logs, and whether another task already occupies the worker.
  • If the worker can’t authenticate, check its environment key. The Console API key used by the session client is a different credential.
  • If a tool is missing, build an image with the required dependencies. The example uses a Python image and doesn’t install a project-specific toolchain.
Tool inputs and outputs flow to Anthropic even though execution happens on CoreWeave. Managed Agents isn’t eligible for Zero Data Retention or HIPAA Business Associate Agreement coverage. See Anthropic’s data-retention eligibility. Review the self-hosted environment security model for data handling and worker permissions.
Last modified on September 17, 2026