My name is Abhishek. I've spent my career working on Operating Systems and Infrastructure at places like Replit, Google, and Microsoft.
Today, I'm excited to launch Arrakis: an open-source and self-hostable sandboxing service designed to let AI Agents execute code and operate a GUI securely.
GitHub: https://github.com/abshkbh/arrakis
Watch Claude build a live Google Docs clone using Arrakis via MCP – with no re-prompting or interruption. https://www.youtube.com/watch?v=IZ5cAnhAdPQ
Key Features
- Self-hostable: Run it on your own infra or Linux server.
- Secure by Design: Uses MicroVMs for strong isolation between sandbox instances.
- Snapshotting & Backtracking: First-class support allows AI agents to snapshot a running sandbox (including GUI state!) and revert if something goes wrong.
- Ready to Integrate: Comes with a Python SDK (https://pypi.org/project/py-arrakis/) and an MCP server (https://github.com/abshkbh/arrakis-mcp-server) out of the box.
- Customizable: Docker-based tooling makes it easy to tailor sandboxes to your needs.
Sandboxes = Smarter Agents
As the demo shows, AI agents become incredibly capable when given access to a full Linux VM environment. They can debug problems independently and produce working results with minimal human intervention.
I'm the solo founder and developer behind Arrakis. I'd love to hear your thoughts, answer any questions, or discuss how you might use this in your projects!
Get in touch
- Email: abshkbh AT gmail DOT com - LinkedIn: https://www.linkedin.com/in/abshkbh/
Looking forward to your feedback!
