team

marvin.agents.team

Classes

RandomTeam

class RandomTeam(name: str = lambda: random.choice(TEAM_NAMES)(), instructions: str | None = None, description: str | None = 'A team of agents that randomly selects an agent to act.', verbose: bool = False, prompt: str | Path = Path('team.jinja'), members: list[Actor], delegates: dict[Actor, list[Actor]] = dict())

Methods:

• start_turn
  def start_turn(self, thread: Thread)
  

RoundRobinTeam

class RoundRobinTeam(name: str = lambda: random.choice(TEAM_NAMES)(), instructions: str | None = None, description: str | None = 'A team of agents that rotate turns.', verbose: bool = False, prompt: str | Path = Path('team.jinja'), members: list[Actor], delegates: dict[Actor, list[Actor]] = dict())

Methods:

• start_turn
  def start_turn(self, thread: Thread)
  

Swarm

class Swarm(name: str = lambda: random.choice(TEAM_NAMES)(), instructions: str | None = None, description: str | None = None, verbose: bool = False, prompt: str | Path = Path('team.jinja'), members: list[Actor], delegates: dict[Actor, list[Actor]] = dict())

A swarm is a team that permits all agents to delegate to each other.

Team

class Team(name: str = lambda: random.choice(TEAM_NAMES)(), instructions: str | None = None, description: str | None = None, verbose: bool = False, prompt: str | Path = Path('team.jinja'), members: list[Actor], delegates: dict[Actor, list[Actor]] = dict())

A team is a container that maintains state for a group of agents.

Methods:

• end_turn
  def end_turn(self, thread: Thread, result: AgentRunResult)
  

• friendly_name
  def friendly_name(self, verbose: bool = True) -> str
  

• get_agentlet
  def get_agentlet(self, tools: list[Callable[..., Any]], end_turn_tools: list[EndTurn]) -> pydantic_ai.Agent[Any, Any]
  

• get_end_turn_tools
  def get_end_turn_tools(self) -> list[EndTurn]
  

• get_memories
  def get_memories(self) -> list[Memory]
  

• get_prompt
  def get_prompt(self) -> str
  

• start_turn
  def start_turn(self, thread: Thread)
  

---

Parent Module: agents