Concepts
This section covers the core concepts of the AI Agents library. Understanding these concepts is essential for building robust and scalable AI agent systems.
Overview
The AI Agents library is built around several key concepts that work together to provide a powerful framework for multi-agent AI workflows:
- Agents - Immutable, thread-safe AI assistants with specific roles and capabilities
- AgentRunner - Thread-safe execution manager for multi-agent conversations
- Context - Serializable state management that persists across agent interactions
- Handoffs - Tool-based mechanism for seamless agent transitions
- Tools - Stateless extensions for external system integration
- AgentTool - Agent-to-agent collaboration without conversation handoffs