OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across files and tools.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
How OpenAI built an agent runtime using the Responses API, shell tool, and hosted containers to run secure, scalable agents with files, tools, and state.
OpenAI introduces Aardvark, an AI-powered security researcher that autonomously finds, validates, and helps fix software vulnerabilities at scale. The system is in private beta—sign up to join early testing.
OpenAI plans to acquire Ona to expand Codex with secure, persistent cloud environments, enabling long-running AI agents across enterprise workflows.
We’re releasing an API for accessing new AI models developed by OpenAI.
OpenAI co-founds the Agentic AI Foundation under the Linux Foundation and donates AGENTS. md to support open, interoperable standards for safe agentic AI.
Stateful Runtime for Agents in Amazon Bedrock brings persistent orchestration, memory, and secure execution to multi-step AI workflows powered by OpenAI.