Arrakis (https://github.com/abshkbh/arrakis) provides MicroVM-based secure sandboxes for code execution and full computer use. It features first-class support for backtracking, a Python SDK, and a Model Context Protocol (MCP) server.

In this talk, we go under the hood to explore how to architect an AI sandbox from the ground up. We’ll also dive into why sandboxes are becoming essential infrastructure for AI models and agents — enabling the next big unlock in intelligence.

Links -
Slides for the talk available here - https://tinyurl.com/arrakis-aie
Vibe coding with Claude and Arrakis -https://x.com/abshkbh/status/1907480355529203809

AI Engineer

Abhishek Bhardwaj explains how to build Arrakis, an open-source AI sandbox service that uses microVMs for secure code execution. The presentation covers Linux sandboxing fundamentals, comparing containers vs virtualization, and details the architecture including overlay filesystems, networking setup, and snapshot/restore capabilities. MicroVMs provide better security than containers by isolating guest kernels while maintaining fast boot times under 7 seconds. The system enables AI agents to execute code safely, backtrack on failures, and handle multi-step workflows through checkpointing.

Arrakis: How To Build An AI Sandbox From Scratch - Abhishek Bhardwaj