OpenAI Agents SDK adds native sandbox execution
aiengineer
feature
OpenAI has updated its Agents SDK to include native sandbox execution and a model-native harness. This enhancement aims to help developers build more secure, long-running agents that can interact with files and tools. The update is now available for use.
Features (1) ›
- Native sandbox execution for Agents SDK
The Agents SDK now features native sandbox execution and a model-native harness. This allows developers to build agents that can securely run for extended periods and access files and tools.
Read the original announcement →
https://openai.com/index/the-next-evolution-of-the-agents-sdk
Related releases
- OpenAI Disrupts Cambodia-Based Scam Operation OpenAI News ·
- openai-python v2.52.0 adds content provenance checks OpenAI Python SDK Releases ·
- OpenAI's Full-Stack Approach to Advanced AI OpenAI News ·
- Univé Builds AI-Ready Workforce with ChatGPT Enterprise OpenAI News ·
- OpenAI Discusses Responsible AI Practices for Europe OpenAI News ·
- Avatarin uses OpenAI GPT-Realtime for 24/7 retail customer support OpenAI News ·