Agent Crews

An Agent Crew is the core building block that powers conversational AI in the Atoms Agent Crews SDK. It’s the “brain” that listens to what users say, thinks about how to respond, and speaks back — in real-time, with one or many cooperating nodes.

What is an Agent Crew?

In Atoms, the simplest crew is a single OutputCrewNode—a specialized node that handles the complete conversation loop:

Listen — Receives transcribed speech from the user
Think — Processes the input with an LLM to generate a response
Speak — Streams the response as audio back to the user

This happens continuously, creating a natural back-and-forth conversation.

Why Atoms Agent Crews?

Feature	Description
Real-Time Streaming	Responses start playing while the LLM is still generating. No waiting.
Interruption Handling	When users speak mid-response, the agent stops and listens.
Context Management	Conversation history maintained automatically.
Tool Calling	Execute functions mid-conversation—check databases, call APIs.
Multi-Provider LLM	Use Smallest’s own Electron, OpenAI, Anthropic, or any OpenAI-compatible endpoint.
Production Ready	Deploy with one command. Handle thousands of concurrent calls.

Node Types

The SDK provides three node types for building agent crews:

Node	Purpose
`CrewNode`	Base primitive for routing, logging, and custom logic
`OutputCrewNode`	Conversational agent that speaks to users
`BackgroundCrewNode`	Silent observer for analytics and monitoring