Building AI agents, atomically
API Reference
This section contains the API reference for all public modules and classes in Atomic Agents.
:maxdepth: 2
:caption: API Reference
agents
context
utils
Core Components
The Atomic Agents framework is built around several core components that work together to provide a flexible and powerful system for building AI agents.
Agents
The agents module provides the base classes for creating AI agents:
AtomicAgent: The foundational agent class that handles interactions with LLMsAgentConfig: Configuration class for customizing agent behaviorBasicChatInputSchema: Standard input schema for agent interactionsBasicChatOutputSchema: Standard output schema for agent responses
Context Components
The context module contains essential building blocks:
ChatHistory: Manages conversation history and state with support for:- Message history with role-based messages
- Turn-based conversation tracking
- Multimodal content
- Serialization and persistence
- History size management
SystemPromptGenerator: Creates structured system prompts with:- Background information
- Processing steps
- Output instructions
- Dynamic context through context providers
BaseDynamicContextProvider: Base class for creating custom context providers that can inject dynamic information into system prompts
Learn more about context components
Utils
The utils module provides helper functions and utilities:
- Message formatting
- Tool response handling
- Schema validation
- Error handling
Getting Started
For practical examples and guides on using these components, see: