Arrakis – Open-source, self-hostable sandboxing service for AI Agents
Hi HN! 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…
In plain words
Arrakis is an open-source, self-hostable sandboxing service that enables AI agents to safely execute code and interact with graphical interfaces. Built by someone with infrastructure experience at major tech companies, it uses MicroVMs for isolation between sandbox instances and supports snapshotting and reverting states. The service can run on users' own infrastructure or Linux servers and includes a Python SDK for integration with AI systems.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! 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!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
