Autonomous Looper with Bash

​

When to use it

• The agent needs to run CLI commands (e.g. ls, python script.py, git status).
• You use max_loops="auto" and want the agent to have terminal access.
• You want to keep other tools restricted and only add bash execution.

​

Enable the tool

from swarms import Agent

agent = Agent(
    agent_name="Terminal-Agent",
    agent_description="Agent that can run bash commands on the terminal",
    model_name="anthropic/claude-sonnet-4-6",
    max_loops="auto",
    dynamic_context_window=True,
    selected_tools=[
        "create_plan",
        "subtask_done",
        "complete_task",
        "respond_to_user",
        "read_file",
        "list_directory",
        "run_bash",
    ],
)

​

Run a task

result = agent.run(
    task="Use the terminal to list the current directory, then run 'echo Hello from bash' and report the output."
)
print(result)

​

Tool parameters

​

Limits and safety checks

• Length: commands over 512 characters are refused. If the command is a heredoc or redirect, the refusal tells the model to write the file with create_file or update_file instead, so give the agent those tools when it needs to write files.
• Blocklist: commands matching dangerous patterns are refused, including recursive rm, piping into a shell or interpreter, sudo, shutdown and reboot, printenv, curl -d, redirects into /etc or /usr, and redirects to disk devices or /dev/null.
• Output cap: the result is capped at a quarter of the agent’s context_length in tokens, with a marker saying how much was cut. Set context_length lower for a tighter cap.
• Searches: for finding files or matching text, the glob and grep tools are preferred over find and grep through bash.

​

Example file

examples/single_agent/capabilities/autonomy/autonomous_agents/example_autonomous_looper_run_bash.py

​

See also

• Autonomous Looper Tools – Configuring selected_tools
• Autonomous Mode – How the loop plans, runs tools and stays bounded
• Agent Reference – selected_tools and autonomous loop