Project Lightning Talk: Run Sandbox Securely and Cost-Effectively With OpenKruise Agents
Lightningat KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 · 2026-09-07..09-09·
summary
Covers running production sandboxes for LLM-generated untrusted code and the security/latency/cost trade-offs. Describes using OpenKruise Agents with a warm pool that supports horizontal and vertical elasticity, an agent gateway that injects tokens on the fly, and sandbox pause-and-resume techniques; mentions using Envoy and OpenKruise in-place update as part of the solution.
AI-written summary · about
related talks
14mTaming Agentic AI: Run Rogue Code Safely on Kubernetes with Agent Sandbox
39mTrust, but Sandbox: Securing AI Agents in Kubernetes
29mSandbox for Agentic Application With Cloud Native Stack
06mLightning Talk: OpenKruise: Advancing Kubernetes Workload Auto...
30mSandboxing Agentic AI With LSM-BPF
27mKeeping Your Agents in Check: Layered Security for Agentic Platforms in Production
11mBuilding Secure Backend Services with AI Agents
34mZero Secrets: Building Secure Infrastructure for AI Agents