Home Multikernel Cloud Multikernel Sandbox Multikernel LiveUpdate Technology Roadmap FAQ Getting Started Blog About GitHub Schedule a Demo

Latest Insights

Stay updated with the latest developments in multikernel technology, cloud computing, and operating system innovation.

AI Agent Sandboxes Got Security Wrong

The industry is spending millions on microVMs and container runtimes to sandbox AI agents. But the threat model is wrong. Agents are not adversaries. Isolation is not security. Most agents...

One Pipe, Two Sandboxes, Zero Prompt Injection

Sandlock introduces sandbox pipelines: chain sandboxed stages with the | operator, where each stage has its own Landlock and seccomp policy. Data flows through kernel pipe buffers the parent process...

Per-Tool Sandboxing for AI Agents: Why One Sandbox Is Not Enough

Container-based agent sandboxes give every tool the same permissions. Sandlock now supports per-tool-call kernel-enforced isolation: each tool gets only the capabilities it declares. Deny by default, least privilege per call....

Processes Are All You Need for AI Sandboxing

Containers and microVMs start from scratch. Processes start from a copy. We explain why fork() and copy-on-write memory are the right primitives for AI sandboxing, and introduce Sandlock, a lightweight...