Skip to content

[`agentic_crew.runners.single_agent_runner`](#module-agentic_crew.runners.single_agent_runner)

Single-agent runner base class.

Single-agent runners execute simple, sequential tasks without multi-agent collaboration overhead. They’re ideal for:

  • Quick file edits
  • Code generation
  • Local development
  • Sequential workflows

Unlike multi-agent crews, single-agent runners:

  • Take a single task string as input
  • Execute in one pass without delegation
  • Return results directly
  • Have minimal configuration overhead
SingleAgentRunnerBase class for single-agent runners.

class agentic_crew.runners.single_agent_runner.SingleAgentRunner

Section titled “class agentic_crew.runners.single_agent_runner.SingleAgentRunner”

Bases: abc.ABC

Base class for single-agent runners.

Single-agent runners provide a simpler execution model than multi-agent crews. They execute a single task and return the result, without the complexity of agent collaboration, delegation, or hierarchical processes.

‘single_agent’

Execute a single task and return the result.

Args: task: The task to execute (e.g., “Add error handling to auth.py”). working_dir: Optional working directory for execution. **kwargs: Additional runner-specific parameters.

Returns: Task output as a string.

Raises: RuntimeError: If execution fails.

Check if this runner is available (dependencies installed, etc.).

Returns: True if the runner can be used.

Get list of required environment variables.

Returns: List of environment variable names required by this runner.