> ## Documentation Index > Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt > Use this file to discover all available pages before exploring further. # Claude Managed Agents에서 Sandboxes 사용하기 > 셀프 호스팅 샌드박스 워커를 Claude Managed Agents에 연결하고 CoreWeave에서 도구 실행을 확인하세요. Connect [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) 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. 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](https://platform.claude.com/docs/en/managed-agents/overview#beta-access). ## Prerequisites Before you begin, you need the following: * [W\&B API 키](https://forge.coreweave.com/settings#apikeys). 이 예시에서는 W\&B 인증을 사용합니다. * Anthropic 워크스페이스의 Claude Managed Agents 액세스 권한, 그리고 세션을 생성하는 클라이언트에서 사용할 Console API 키. * `agent_toolset_20260401`로 설정된 기존 에이전트. Anthropic의 [Managed Agents 퀵스타트](https://platform.claude.com/docs/en/managed-agents/quickstart)를 참고해 에이전트를 생성하고 에이전트 ID를 기록해 두세요. * SDK 예시를 실행하려면 [`uv`](https://docs.astral.sh/uv/)가 설치된 Python 3.11 이상 또는 Node.js 22 이상. 이 가이드를 진행할 터미널에서 W\&B API 키를 export하세요. `cws-agent`가 W\&B 인증을 사용하도록 설정된 CoreWeave 토큰은 모두 unset하세요: ```bash theme={"system"} export WANDB_API_KEY="[WANDB-API-KEY]" unset CWSANDBOX_API_KEY ``` ## Create an environment In the [Claude Console](https://platform.claude.com/environments), 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](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#create-a-self-hosted-environment). 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 [`cws-agent` 설치 안내](https://github.com/coreweave/cws-agent#install)에 따라 설치하세요. 이 도구는 [파일 시스템 스냅샷](/products/sandboxes/serverless/file-system-snapshots#start-a-sandbox-with-a-snapshot-mount)으로 워크스페이스를 저장하고 복원하는 데 사용할 스냅샷 볼륨을 설정합니다. 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: ```bash theme={"system"} export ANTHROPIC_ENVIRONMENT_KEY="[ENVIRONMENT-KEY]" cws-agent launch [SANDBOX-NAME] --claude-env [ENVIRONMENT-ID] ``` Launch starts one worker in `/workspace/claude/0` and returns to your shell. The tool passes the environment key into the sandbox. To view the worker's terminal, run: ```bash theme={"system"} cws-agent connect [SANDBOX-NAME] --cmd 'tmux attach -t claude-0' ``` Detach with **Ctrl-b**, then **d**. Continue to [Run and verify a task](#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: ```bash theme={"system"} export ANTHROPIC_ENVIRONMENT_KEY="[ENVIRONMENT-KEY]" export ANTHROPIC_ENVIRONMENT_ID="[ENVIRONMENT-ID]" ``` Python 3.11 이상과 `uv`를 사용하세요. ```bash theme={"system"} uv venv --python 3.11 source .venv/bin/activate uv pip install 'cwsandbox[wandb]>=1.14.2' ``` Node.js 22 이상을 사용하세요. 프로젝트에 클라이언트와 TypeScript 러너를 설치하세요. ```bash theme={"system"} npm install @coreweave/cwsandbox@0.5.0-beta.0 tsx ``` ### 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. ```python title="start_claude_worker.py" theme={"system"} import os from cwsandbox import AuthStrategy, Sandbox worker = """ set -o pipefail case "$(uname -m)" in x86_64) arch=amd64 ;; aarch64) arch=arm64 ;; *) echo "Unsupported architecture" >&2; exit 1 ;; esac version=1.33.0 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${version}/ant_${version}_linux_${arch}.tar.gz" \ | tar -xz -C /usr/local/bin ant mkdir -p /workspace exec ant beta:worker poll --workdir /workspace """ sandbox = Sandbox.run( "bash", "-ec", worker, auth=AuthStrategy.WANDB, container_image="python:3.12-bookworm", environment_variables={ "ANTHROPIC_ENVIRONMENT_KEY": os.environ["ANTHROPIC_ENVIRONMENT_KEY"], "ANTHROPIC_ENVIRONMENT_ID": os.environ["ANTHROPIC_ENVIRONMENT_ID"], }, resources={"cpu": "2", "memory": "4Gi"}, max_lifetime_seconds=8 * 3600, tags=["claude-managed-agents-worker"], ) try: sandbox.wait() except BaseException: sandbox.stop().result() raise print(f"Worker sandbox ID: {sandbox.sandbox_id}") ``` ```typescript title="start_claude_worker.mts" theme={"system"} import { createSandboxClientFromEnv } from "@coreweave/cwsandbox/wandb"; const token = process.env.ANTHROPIC_ENVIRONMENT_KEY; if (!token) throw new Error("Set ANTHROPIC_ENVIRONMENT_KEY."); const environmentId = process.env.ANTHROPIC_ENVIRONMENT_ID; if (!environmentId) throw new Error("Set ANTHROPIC_ENVIRONMENT_ID."); const worker = ` set -o pipefail case "$(uname -m)" in x86_64) arch=amd64 ;; aarch64) arch=arm64 ;; *) echo "Unsupported architecture" >&2; exit 1 ;; esac version=1.33.0 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v\${version}/ant_\${version}_linux_\${arch}.tar.gz" \\ | tar -xz -C /usr/local/bin ant mkdir -p /workspace exec ant beta:worker poll --workdir /workspace `; const client = createSandboxClientFromEnv(); const sandbox = await client.run(["bash", "-ec", worker], { containerImage: "python:3.12-bookworm", environmentVariables: { ANTHROPIC_ENVIRONMENT_KEY: token, ANTHROPIC_ENVIRONMENT_ID: environmentId, }, resources: { cpu: "2", memory: "4Gi" }, maxLifetimeSeconds: 8 * 3600, waitUntilRunning: false, tags: ["claude-managed-agents-worker"], }); try { await sandbox.wait(); } catch (error) { await sandbox.stop(); throw error; } console.log(`Worker sandbox ID: ${sandbox.sandboxId}`); ``` Run the script: ```bash theme={"system"} python start_claude_worker.py ``` ```bash theme={"system"} npx tsx start_claude_worker.mts ``` 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: ```python theme={"system"} from cwsandbox import AuthStrategy, Sandbox sandbox = Sandbox.from_id("[SANDBOX-ID]", auth=AuthStrategy.WANDB).result() print("Sandbox status:", sandbox.get_status()) for container in sandbox.container_statuses: print(container.name, container.state, container.exit_code, container.restart_count) for line in sandbox.stream_logs(tail_lines=100): print(line, end="") ``` ```typescript theme={"system"} import { createSandboxClientFromEnv } from "@coreweave/cwsandbox/wandb"; const client = createSandboxClientFromEnv(); const sandbox = await client.fromId("[SANDBOX-ID]"); console.log("Sandbox status:", sandbox.status, "Exit code:", sandbox.exitCode); for (const line of await sandbox.logs.read({ tailLines: 100 })) { process.stdout.write(line); } ``` 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](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes).

선택: 시크릿 저장소 사용

환경 키 값 대신 [W\&B 시크릿 참조](/ko/products/sandboxes/serverless/secrets)를 전달할 수 있습니다. SDK 예시는 이미 W\&B 인증을 사용하도록 되어 있습니다. 환경 키를 담당 W\&B 팀의 Secret Manager에 저장하고, 해당 팀이 기본 entity가 아니라면 `WANDB_ENTITY`로 그 팀을 지정하세요. `[SECRET-NAME]`을 팀 시크릿 이름으로 바꾸세요. `cwsandbox`에서 `Secret`을 임포트하고, `environment_variables`에서 `ANTHROPIC_ENVIRONMENT_KEY`를 제거한 다음 `Sandbox.run()`에 `secrets=[Secret(store="wandb", name="[SECRET-NAME]", env_var="ANTHROPIC_ENVIRONMENT_KEY")]`를 추가하세요. `const token` 선언과 해당 `if (!token)` 검사를 제거하세요. `environmentVariables`에서 `ANTHROPIC_ENVIRONMENT_KEY`를 제거하고, `client.run()`에 전달하는 옵션에 `secrets: [{ store: "wandb", name: "[SECRET-NAME]", envVar: "ANTHROPIC_ENVIRONMENT_KEY" }]`를 추가하세요. 플랫폼이 참조를 해석한 뒤 워커의 환경 변수를 설정합니다. ## Run and verify a task Run the session client on your own machine for either setup path. Install the Anthropic SDK for your language: ```bash theme={"system"} uv venv --python 3.11 .claude-client source .claude-client/bin/activate uv pip install 'anthropic>=1.6.0' ``` ```bash theme={"system"} npm install @anthropic-ai/sdk@0.126.0 tsx ``` 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: ```bash theme={"system"} export ANTHROPIC_API_KEY="[ANTHROPIC-API-KEY]" export ANTHROPIC_AGENT_ID="[AGENT-ID]" export ANTHROPIC_ENVIRONMENT_ID="[ENVIRONMENT-ID]" ``` 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. ```python title="verify_claude_worker.py" theme={"system"} import os import uuid from anthropic import Anthropic client = Anthropic() proof = uuid.uuid4().hex session = client.beta.sessions.create( agent=os.environ["ANTHROPIC_AGENT_ID"], environment_id=os.environ["ANTHROPIC_ENVIRONMENT_ID"], title="CoreWeave worker verification", ) print(f"Session ID: {session.id}") print(f"Expected file contents: {proof}") events_by_id = {} with client.beta.sessions.events.stream(session.id) as events: client.beta.sessions.events.send( session.id, events=[{ "type": "user.message", "content": [{ "type": "text", "text": f"Write exactly {proof} to managed-agent-proof.txt in your working directory and read it back.", }], }], ) for event in events: print(event.model_dump_json()) events_by_id[event.id] = event if event.type == "session.status_idle": reason = event.stop_reason if reason and reason.type == "requires_action": pending = [events_by_id.get(event_id) for event_id in reason.event_ids] if pending and all( getattr(tool, "evaluated_permission", None) == "allow" for tool in pending ): continue break ``` ```typescript title="verify_claude_worker.mts" theme={"system"} import { randomUUID } from "node:crypto"; import Anthropic from "@anthropic-ai/sdk"; const agent = process.env.ANTHROPIC_AGENT_ID; const environmentId = process.env.ANTHROPIC_ENVIRONMENT_ID; if (!agent || !environmentId) { throw new Error("Set ANTHROPIC_AGENT_ID and ANTHROPIC_ENVIRONMENT_ID."); } const client = new Anthropic(); const proof = randomUUID().replaceAll("-", ""); const session = await client.beta.sessions.create({ agent, environment_id: environmentId, title: "CoreWeave worker verification", }); console.log(`Session ID: ${session.id}`); console.log(`Expected file contents: ${proof}`); const allowedEvents = new Map(); await client.beta.sessions.events.send(session.id, { events: [{ type: "user.message", content: [{ type: "text", text: `Write exactly ${proof} to managed-agent-proof.txt in your working directory and read it back.`, }], }], }); const events = await client.beta.sessions.events.stream(session.id); try { for await (const event of events) { console.log(JSON.stringify(event)); if ("id" in event) { allowedEvents.set(event.id, "evaluated_permission" in event && event.evaluated_permission === "allow"); } if (event.type === "session.status_idle") { const reason = event.stop_reason; if (reason?.type === "requires_action" && reason.event_ids.length > 0 && reason.event_ids.every((id) => allowedEvents.get(id) === true)) { continue; } break; } } } finally { events.controller.abort(); } ``` Run it and inspect the events: ```bash theme={"system"} python verify_claude_worker.py ``` ```bash theme={"system"} npx tsx verify_claude_worker.mts ``` If the script stops with `requires_action`, inspect the referenced tool events. Calls with `evaluated_permission: "ask"` need Anthropic's [tool-confirmation workflow](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#tool-confirmation). 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: ```bash theme={"system"} cws-agent exec [SANDBOX-NAME] 'cat /workspace/claude/0/managed-agent-proof.txt' ``` ```python theme={"system"} from cwsandbox import AuthStrategy, Sandbox sandbox = Sandbox.from_id("[SANDBOX-ID]", auth=AuthStrategy.WANDB).result() result = sandbox.exec(["cat", "/workspace/managed-agent-proof.txt"], check=True).result() print(result.stdout, end="") ``` ```typescript theme={"system"} import { createSandboxClientFromEnv } from "@coreweave/cwsandbox/wandb"; const client = createSandboxClientFromEnv(); const sandbox = await client.fromId("[SANDBOX-ID]"); const result = await sandbox.commands.run(["cat", "/workspace/managed-agent-proof.txt"], { check: true }); process.stdout.write(result.stdout); ``` 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: ```bash theme={"system"} cws-agent down [SANDBOX-NAME] ``` `down`은 중지하기 전에 워크스페이스 스냅샷을 생성합니다. 캡처에 실패하면 `cws-agent status [SANDBOX-NAME]`을 확인하고 원인을 해결한 뒤 다시 시도하세요. 저장되지 않은 변경 사항을 버려도 된다면 `down --no-snapshot`을 사용하세요. ```python theme={"system"} from cwsandbox import AuthStrategy, Sandbox sandbox = Sandbox.from_id("[SANDBOX-ID]", auth=AuthStrategy.WANDB).result() sandbox.stop().result() ``` ```typescript theme={"system"} import { createSandboxClientFromEnv } from "@coreweave/cwsandbox/wandb"; const client = createSandboxClientFromEnv(); const sandbox = await client.fromId("[SANDBOX-ID]"); await sandbox.stop(); ``` 이 예제에서는 영구 저장소를 설정하지 않으므로, 중지하기 전에 파일을 외부로 복사해 두세요. 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](https://platform.claude.com/docs/en/managed-agents/overview#beta-access). Review the [self-hosted environment security model](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-security) for data handling and worker permissions.