For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.

Suggested

Home

Topics

Contribute

Cookbook on GitHub

Agents

Agents are systems that independently accomplish tasks on your behalf. Agents use an LLM to execute instructions and make decisions. They have access to tools to gather context and take actions, always operating within clearly defined guardrails.

FunctionsAgents SDKResponses

All recipes25

Build a per-run spending controller with the Responses API

Controlled Agentic Commerce with AgentCore Payments

Agents SDKSecurity

Combining security scanners with the Agents SDK

Agents SDKSecurity

Iterating Development Workflows with Codex

AML Analysis with the Agents SDK on Amazon Bedrock

Agents SDKEvalsSecurity

Enabling Long-Term Agent Memory with Oracle AI Agent Memory

Trigger a Workspace Agent from the API

SchemaFlow: Agentic Database Change Impact Analysis, SQL Generation, and Eval Guardrails

Agents SDKEvals

Getting Started with OpenAI Models on Amazon Bedrock

Macro Evals for Agentic Systems

Build an Agent Improvement Loop with Traces, Evals, and Codex

Agents SDKCodexEvals

Build iterative repair loops with Codex

Using Goals in Codex

Migrate from the Claude Agent SDK to the OpenAI Agents SDK

Agents SDKSecurity

Agents SDK Deployment Manager

Building Reliable Agents with Memory and Compaction

Building workspace agents in ChatGPT to complete repeatable, end-to-end work

ChatGPTSecurity

Computer Use Agents in Daytona Sandboxes

Agents SDKSecurity

Migrate a Legacy Codebase with Sandbox Agents

Agents SDKEvalsSecurity

Codex Prompting Guide

Realtime Eval Guide

AudioEvalsResponsesSpeech

Context Engineering for Personalization - State Management with Long-Term Memory Notes

Context Engineering - Short-Term Memory Management with Sessions

GPT-5 Prompt Migration and Improvement Using the New Optimizer

ReasoningResponses

Temporal Agents with Knowledge Graphs

FunctionsResponses