Design Principles
The Agents SDK is designed to provide a flexible, scalable, and efficient framework for building, testing, and deploying LLM agents. This article discusses the key design principles and goals that guided the development of the SDK.
Agents SDK Architecture
This page is the deep reference for how the built-in agent works internally. It covers the dependency injection system, the provider-source composition pattern, the agent execution loop, and the cross-cutting concerns that tie everything together. For the conceptual overview, see How the Agent Harness Works. For the design rationale, see Design Principles.
Citation Architecture
Citations are the contract that lets an answer be traced back to the objects it drew from: a retrieved chunk, a web result, a tag, a note, or any other resource the agent can surface. This page describes the four layers that implement that contract, how state flows between them, and what a component must do to make its objects citable. For the surrounding execution model, see Agents SDK Architecture.
Creating Custom Sources
Add custom tool, skill, context, memory, instruction, or processor sources that plug into the built-in agent.
Streaming Tool Progress
Provide real-time feedback to users when agents execute tools.
Custom Agent Development
6 items
Making Dependencies Resumable
Implement ResumableAgentDependency so an injected dependency can checkpoint its working state and survive a process restart mid-turn.
Persisting Conversations and State
Reconnects that land on other replicas, crashed producers, second screens - the problems of a horizontally scaled agent deployment, and the storage interfaces that answer them.
Extending the API Server
Add custom endpoints and middleware to the API server.
Configuring Orchestrator agent (Legacy)
Configure Zeta Alpha orchestrator agent in tenant settings