Show HN: Pve-agents – coding agents on your existing Proxmox infrastructure

A developer released pve-agents, a tool that spins up disposable LXC containers on an existing Proxmox host, starts a Claude Code agent inside each one, and streams the full transcript including tool calls to the browser over SSE, replayed from the beginning for late viewers. Each workspace runs in its own container from the same clean template, so agents run in parallel without touching the user's workstation, with permission prompts answered in the browser and per-file diffs shown in a side rail. Users supply a repository, a ref and a purpose, then push results to a branch of the workspace's own or discard them.

Watch The transcript streams Tool calls and all, over SSE, replayed from the beginning for whoever opens the page late. Give it a repository, a ref and a purpose. It builds a disposable LXC on your Proxmox host, starts a Claude Code agent inside it, and streams the whole thing to your browser. Run as many as your host will hold. Each workspace is its own container, so nothing an agent does touches your workstation. Every one starts from the same clean template, they run in parallel rather than in turn, and the hardware is already yours. Permission prompts are answered where you already are, not in a terminal somebody has to be attached to. Per-file diffs in the rail. Push to a branch of the workspace's own, or throw the lot away.