How OpenAI Cut Agent Latency With WebSockets and Smarter Caching
OpenAI’s Responses API now uses WebSockets and connection-scoped caching to slash overhead in agentic loops like Codex. Here’s what changed and why it matters.
Responses API
Read More
OpenAI Turns the Responses API Into a Full Agent Runtime
OpenAI has equipped its Responses API with a shell tool and hosted containers, turning it into a full agent runtime. Here’s what that means for developers.