> ## Documentation Index
> Fetch the complete documentation index at: https://docs.browser-use.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Managed Agents

> Give Anthropic's Claude Managed Agents a stealth cloud browser via the Browser Use CLI.

[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents) run on Anthropic's hosted platform. Install the `browser-use` CLI in the agent's environment and it can drive a stealth cloud browser — with proxies, CAPTCHA solving, live view, and recording. Your API key stays in a credential vault; the model never sees it.

The sandbox can't run a local browser, so the agent starts a named Browser Use Cloud browser and drives it with `browser-use <<'PY'` Python snippets.

## 1. Create an environment

Pre-install the CLI so it's ready at session start (no runtime install).

```yaml theme={null}
name: browser-env
config:
  type: cloud
  packages:
    pip:
      - browser-use
  networking:
    type: limited
    allowed_hosts: ["*.browser-use.com"]
    allow_package_managers: true
```

## 2. Create a credential vault

Store your key as an environment variable so the CLI reads it and the model never does. Get one at [cloud.browser-use.com/settings](https://cloud.browser-use.com/settings?tab=api-keys\&new=1).

| Field | Value                 |
| ----- | --------------------- |
| Type  | Environment variable  |
| Name  | `BROWSER_USE_API_KEY` |
| Value | `bu_...`              |

## 3. Create the agent

Tell it to use the CLI in cloud mode.

```yaml theme={null}
name: browser agent
model:
  id: claude-opus-4-8
description: Drives a stealth cloud browser with the Browser Use CLI.
system: |
  You are a browser agent. Use the `browser-use` CLI to complete web tasks.
  Never launch a local browser in this sandbox. Start a named cloud browser:
  browser-use <<'PY'
  start_remote_daemon("managed")
  PY
  Then run browser work through the same name:
  BU_NAME=managed browser-use <<'PY'
  new_tab("https://example.com")
  print(page_info())
  PY
  Your BROWSER_USE_API_KEY is in the environment; never print it.
tools:
  - type: agent_toolset_20260401 # shell access so the agent can run the CLI
    default_config:
      enabled: true
      permission_policy:
        type: always_allow
```

## 4. Start a session and send a task

The Console only observes; kick the agent off with a `user.message` event.

```bash theme={null}
curl -sS "https://api.anthropic.com/v1/sessions/$SESSION_ID/events?beta=true" \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: managed-agents-2026-04-01" \
  -H "content-type: application/json" \
  -d '{"events":[{"type":"user.message","content":[{"type":"text",
       "text":"Get the top 5 Hacker News stories with their links."}]}]}'
```

## 5. Watch it run

The agent starts a named cloud browser, runs Python helper snippets through `browser-use`, then returns the result. The session shows up in [cloud.browser-use.com](https://cloud.browser-use.com) → **Remote Browsers** with a **Live View** and an **mp4 recording**.

<Tip>
  Always use a cloud browser — the Managed Agents sandbox has no GUI, so a local
  browser won't start. Cloud mode also gives you stealth, residential proxies,
  live view, and recording.
</Tip>