Project Lightning Talk: Run Sandbox Securely and Cost-Effectively with OpenKruise... Zhang Zhen

Why watch

This lightning talk explains how to run LLM-generated code sandboxes securely and cost-effectively using OpenKruise Agents. It addresses the three-way trade-off between security, latency, and cost by combining horizontal and vertical elasticity, on-the-fly token injection via an agent gateway, and smart pause-and-resume capabilities. The solution is designed for DevOps engineers and platform teams running production AI/code generation platforms.