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

# External Tool Execution Async

> Execute tools outside the agent in an async environment. You control tool execution externally while the agent handles the rest of the run.

<Steps>
  <Step title="Create a Python file">
    ```python external_tool_execution_async.py theme={null}
    import asyncio
    import subprocess

    from agno.agent import Agent
    from agno.db.sqlite import SqliteDb
    from agno.models.openai import OpenAIResponses
    from agno.tools import tool
    from agno.utils import pprint


    # We have to create a tool with the correct name, arguments and docstring for the agent to know what to call.
    @tool(external_execution=True)
    def execute_shell_command(command: str) -> str:
        """Execute a shell command.

        Args:
            command (str): The shell command to execute

        Returns:
            str: The output of the shell command
        """
        if command.startswith("ls"):
            return subprocess.check_output(command, shell=True).decode("utf-8")
        else:
            raise Exception(f"Unsupported command: {command}")


    agent = Agent(
        model=OpenAIResponses(id="gpt-5.2"),
        tools=[execute_shell_command],
        markdown=True,
        db=SqliteDb(session_table="test_session", db_file="tmp/example.db"),
    )

    run_response = asyncio.run(agent.arun("What files do I have in my current directory?"))
    if run_response.is_paused:
        for requirement in run_response.active_requirements:
            if requirement.needs_external_execution:
                if requirement.tool_execution.tool_name == execute_shell_command.name:
                    print(
                        f"Executing {requirement.tool_execution.tool_name} with args {requirement.tool_execution.tool_args} externally"
                    )
                    # We execute the tool ourselves. You can also execute something completely external here.
                    result = execute_shell_command.entrypoint(
                        **requirement.tool_execution.tool_args
                    )  # type: ignore
                    # We have to set the result on the tool execution object so that the agent can continue
                    requirement.set_external_execution_result(result)

        run_response = asyncio.run(
            agent.acontinue_run(
                run_id=run_response.run_id,
                requirements=run_response.requirements,
            )
        )
        pprint.pprint_run_response(run_response)


    # Or for simple debug flow
    # agent.print_response("What files do I have in my current directory?")

    ```
  </Step>

  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai sqlalchemy
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
        export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run Agent">
    ```bash theme={null}
    python external_tool_execution_async.py
    ```
  </Step>
</Steps>