I have come to appreciate coding agents to be valuable tools for working with computer program code in any capacity, such as learning about any program’s architecture, diagnosing bugs or developing proofs of concept. Depending on the use-case, reviewing each command the agent wants to run can get tedious and time-consuming very quickly. To safely run a coding agent without review, I wanted a Virtual Machine (VM) solution where the agent has no access to my personal files and where it’s no big deal if the agent gets compromised by malware: I can just throw away the VM and start over.
With the advent of agentic coding tools such as OpenCode, Claude Code, Antigravity and Copilot, the security and the lack of it on even modern operating systems has come back into focus or at least should have been for every responsible and informed user of such tools. This post describes an abstract, yet to be built, system that protects users and their data as best as possible.
With the popularity of exe.dev, sprites (from fly.io), and shellbox, one wonders if there is a way to give sandboxed environment on existing, local boxes witho…
Personal website of Abhinav Sarkar
Bookmarked: [michael.stapelberg.ch] Coding Agent VMs on NixOS with microvm.nix https://michael.stapelberg.ch/posts/2026-02-01-coding-agent-microvm-nix/ See more links at https://abhinavsarkar.net/linkblog #linkblog #linkblogging
Or the more tired “One week with Claude Code”-type article. It’s no secret that I’ve been grumpy about the new AI-based coding trend. I’ve been grumpy about the “push from above to use AI or else”. I’ve been grumpy about the eye-rolling hype I see on LinkedIn. I’ve been grumpy about being on the receiving end of vibe-coded PRs that over-engineer solutions to simple problems. I’ve been grumpy about the thought that we are about to see an amount of bloat like we have never imagined before. But, at the same time, I’ve been using LLMs to review my articles, to perform deep research, to generate cover pictures, and before last week, I had even dipped my toes into AI-based coding agents to help me with boring, repetitive tasks. And you know what? I see their promise of increased productivity, yet the amounts of slop I’ve witnessed make me skeptical and I have had little experience with coding agents myself to judge their promised usefulness. So… surprise! Last weekend I decided to start a Claude Code subscription and, after spending a week on it, I am uncomfortably excited to use it more. How has this happened? Let’s take a look at how I ended here, the kinds of mini-projects I worked on throughout this past week, and the (semi-expected) downsides I encountered.