Show HN: Cosplay as a tech lead, using gVisor to sandbox agents

A developer released MIKE, a web-based interface for delegating coding tasks to locally hosted LLMs, built exclusively on models from Google, Meta, Qwen, Poolside and DeepSeek running via llama.cpp on home machines including a Strix Halo and an Nvidia 5090. MIKE sandboxes agents with gVisor, provisions each agent workspace with Git worktrees and a read-only repository mount for context, and targets low-bandwidth and offline use, with notifications for clarification requests, decisions or code ready for review off by default. The developer said the experience improved substantially after DeepSeek's July release and plans to maintain the tool until better tools support similar features.

Hi everyone, This started as an exploration into harnesses and locally hostable LLMs the kind that uses less power than a small electric heater , and I used it as an opportunity to retool. I've tried popular ones like Cline, Claude Code, and Pi, but wanted a different UX and integrated sandboxes. The solution that I've landed on is a responsive web interface where I can quickly drive progress. It feels like a microcosm of my day job: define and delegate tasks, organize using kanban, then review deliverables. And it also feels like the time I used to spend coding is now spent in code review with the agent, so I tried to optimize the UX to make review feel nicer. One of my maybe a bit niche benchmark use-cases is how pleasant it is to make progress on hobby software projects while also out on a hike. This meant specifying low bandwidth usage and offline mode. Now I can jot down an idea, start the task, and at some point down the trail: get a notification that either clarification is needed, a decision needs to be made, or the code is ready for review. I've been having a good time with this. To build MIKE, I exclusively used locally hostable LLMs from Google, Meta, Qwen, Poolside, and DeepSeek hosted with llama.cpp on my machines at home Strix Halo and a 5090 to "compile" the code. The experience has gotten substantially better ever since DeepSeek’s release in July. Side note: I have a soft spot for llama.cpp since it was one of the first that made it possible to run this new tech at home, and its maintainers accepted a tiny improvement I made to error reporting. Oh the joys of having a PR get approved. I plan on maintaining this, at least until similar features are supported by better tools. Until then, hope you find this useful 5 minute demo: https://youtu.be/jexzLkZ50FU https://youtu.be/jexzLkZ50FU p.s. I didn't mention details about the sandbox earlier since most people seem to find this a bit boring. It was one of my critical requirements, and I opted to use an existing battle-tested sandbox. I'm not an expert on how the Linux kernel works, but seeing all the VM escape exploits recently is a bit scary, and I liked gVisor’s approach to the problem. I'm also using Git worktrees to provision the agent’s workspace, as well as a read-only repository mount to provide relevant context when the agent looks for it. off by default Comments URL: https://news.ycombinator.com/item?id=50137043 https://news.ycombinator.com/item?id=50137043 Points: 1 Comments: 0