Core Concepts
Understand the fundamental building blocks of the Daydreams framework.
The Daydreams framework is designed around a set of core concepts that work together to enable autonomous agent behavior. Understanding these concepts is key to effectively building and customizing agents.
This section provides a detailed explanation of each fundamental component:
- Agent Lifecycle: How an agent processes information, makes decisions, and executes tasks in a continuous loop.
- Contexts: The mechanism for managing state, memory, and behavior for specific tasks or interactions.
- Actions: Definable tasks or capabilities that an agent can perform.
- Inputs: How agents receive data and trigger processing cycles.
- Outputs: How agents communicate results or send information to external systems.
- Memory: The different ways agents store, retrieve, and utilize information (Working, Episodic, Vector).
- Prompting: How instructions and context are formatted for the LLM to guide its reasoning.
- Streaming & Parsing: How the framework handles and interprets the LLM's output stream in real-time.
- Task Runner: The system for managing asynchronous operations and background tasks.
- Services & Extensions: How to integrate external services and extend the framework's capabilities.
Explore these pages to gain a deeper understanding of how Daydreams works under the hood.