Tag
OpenAI's Agents API introduces a managed agent runtime, raising questions about which artifacts should remain inspectable to ensure reproducibility and trust in such systems.
A new research architecture for AI agents is introduced, centered on a transparent runtime where every interaction becomes a replayable execution trail with full inspectability, including plan, execute, observe, verify, and remember stages.
Skillerr is a tool that enables running AI agent skills safely and with full inspectability, addressing the risk of executing unknown code from third-party skills.