Lima-devbox – Claude skill for creating a VM dev sandbox on your Mac
As I've increasingly pursued orchestrated agentic coding - I needed a safe way to run Claude Code in YOLO mode on my mac. I looked at a lot of options including Docker but then came across Lima (Linux for Mac) and this great guide by Chris Hager on how create a dev sandbox for your mac using Lima. This creates an Ubuntu VM, mapped to your dev directory with RW access, port and SSH forwarding, Mise support for language installs and automatic code agent installs. https://www.metachris.dev/2025/11/sandbox-your-ai-dev-tools-... I followed his guide. Got it working on my…
What it does
In the maker’s words, at launch
As I've increasingly pursued orchestrated agentic coding - I needed a safe way to run Claude Code in YOLO mode on my mac. I looked at a lot of options including Docker but then came across Lima (Linux for Mac) and this great guide by Chris Hager on how create a dev sandbox for your mac using Lima. This creates an Ubuntu VM, mapped to your dev directory with RW access, port and SSH forwarding, Mise support for language installs and automatic code agent installs. https://www.metachris.dev/2025/11/sandbox-your-ai-dev-tools-... I followed his guide. Got it working on my own then thought I'd try packaging it up in a claude skill to share. And holy yep works great! To setup just go to /plugin -> marketplace in Claude Code and add recodelabs/lima-devbox Then install the skill and ask Claude to create you a VM. Claude will ask you some questions and then proceed to build you your VM. Side note - this really hits home for me that Agent Skills is really all you need. Instead of writing a guide or wrapping this up in a app/TUI just bake any knowledge or process you want to automate and share into a skill. Definitely feels like the future. Would love your feedback and PRs if you have ideas on how to improve. https://github.com/recodelabs/lima-devbox Thanks! Matt
Does the same job
all alternatives →
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 · 27d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
