Replit rebuilt its sandbox engine with microVMs

Replit has overhauled its sandbox infrastructure by migrating to microVMs to improve security and scalability for AI-driven coding agents. This update allows for better isolation of autonomous agents, addressing growing industry concerns regarding AI safety and system containment.
Why it matters
As AI agents become more autonomous, robust sandboxing is critical to prevent them from accessing or damaging sensitive host systems.
Agent sandboxes are all the rage. A new sandbox startup is announced every couple of weeks. At Replit, we’ve been running sandboxes for nearly a decade. For years, we’ve run our custom sandbox infrastructure to make it easy for anyone to code online, and now Agents use these sandboxes to build applications without requiring any coding at all.
In the past few months, we finished rolling out a complete rewrite of our sandbox engine to improve security, capabilities, and portability across clouds. Our Bring Your Own Cloud offering brings Replit into customers’ AWS, Google Cloud, or Azure environments. As with most infrastructure work, we had to pull this off without anyone even noticing. We migrated hundreds of millions of projects smoothly, without data loss. In this post, we’ll dive into how we changed the isolation boundary, kept sandboxes fast, and made the new engine work at scale.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in