Original Summary

Hi everyone,<p>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&#x27;ve tried popular ones like Cline, Claude Code, and Pi, but wanted a different UX and integrated sandboxes.<p>The solution that I&#x27;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.<p>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.<p>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&#x27;ve been having a good time with this.<p>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 generate 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.<p>I plan on maintaining this, at least until similar features are supported by better tools. Until then, hope you find this useful!<p>5 minute demo: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;jexzLkZ50FU" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;jexzLkZ50FU</a><p>p.s.<p>I didn&#x27;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&#x27;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.<p>I&#x27;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.<p>off by default

  • 情报分类：工作与职业机会
  • 分类依据：内容涉及招聘、求职或职业发展
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/18 09:49:34