OpenAI's Agents API gives applications a managed system for running agents over continuing tasks. According to the official overview, OpenAI handles sessions, coordination, context compactionSummarizing an agent's earlier conversation to free room in the context window so a long session can keep going.Full definition → and recovery, while developers provide tools and choose where execution happens.
An application can create a session, submit work, receive progress events and later send another task to that same session. The retained state means it need not reconstruct the conversation each time. This has a deployment consequence: the documentation says the API supports data residency only in the United States and is not eligible for Zero Data Retention, including when the execution environment is self-hosted.
Terms in this piece · Glossary
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
