{"slug": "show-hn-corgi-a-helpful-agent-terminal-multiplexer", "title": "Show HN: Corgi, a helpful {agent, terminal} multiplexer", "summary": "A developer released Corgi, an open agent-and-terminal multiplexer inspired by Herdr, as a Show HN post that had drawn 2 points and 0 comments at the time of the post. Corgi shows a running feed of what each agent is doing, offers an F1 shortcut to jump to the next unread agent, and includes a unified launcher for Codex, Claude Code and Pi with fast session search and resume plus inline usage tracking. The tool adds terminal conveniences including click-to-copy links, cmd+v image pasting that works over SSH, image thumbnail previews, and built-in CPU, memory and GPU usage tracking broken down by workspace, and it reuses the agents themselves to answer questions such as what a given HTTP link or worktree is about.", "body_md": "Hey everyone,\n\nInspired by Herdr, I've built an agent multiplexer that I've been using as my daily driver for a few weeks now.\n\nI think I improved on the concept in a few ways, focusing on the ergonomics I always wished I had:\n\nI show you what the agents are up to, along with a running feed of their activity. There's also a simple shortcut (F1) to go to the next unread agent.\n\nI use multiple accounts, so I've added unified launcher for Codex/Claude Code/Pi. Theres some careful ergonomics there: fast search and resume over sessions, inline usage tracking etc.\n\nMany small quality of life improvements to the terminal experience: - Links can be copied with a click, so no need to drag-select over many lines - cmd+v just pastes images (even on SSH) - images have a thumbnail preview. - Built-in CPU/Memory/GPU usage tracking, broken down by workspace\n\nI assume you have access to cheap inference (Luna/Haiku/etc). It just reuses the agents to organize things for you: what is this http link? what is this worktree about? what is each agent doing? It's small but it made my environment feel more cozy.\n\nOn a personal note, I've been on a frustrating sick leave for a while now. I created Corgi to challenge myself, and see if I can go back. The answer is more mixed than I had hoped, but I am happy with the result and thankful for the experience.\n\nI hope you like it! a few friends & myself have been using it for a few weeks and it's been pretty nice. There's still a lot to improve and some rough edges, so feedback would be greatly appreciated.\n\nThank you :)\n\nComments URL: [https://news.ycombinator.com/item?id=50214373](https://news.ycombinator.com/item?id=50214373)\n\nPoints: 2\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-corgi-a-helpful-agent-terminal-multiplexer", "canonical_source": "https://corgi.computer/", "published_at": "2026-10-23 19:46:38+00:00", "updated_at": "2026-10-23 20:12:42.142359+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-products"], "entities": ["Corgi", "Herdr", "Codex", "Claude Code", "Pi"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-corgi-a-helpful-agent-terminal-multiplexer", "markdown": "https://wpnews.pro/news/show-hn-corgi-a-helpful-agent-terminal-multiplexer.md", "text": "https://wpnews.pro/news/show-hn-corgi-a-helpful-agent-terminal-multiplexer.txt", "jsonld": "https://wpnews.pro/news/show-hn-corgi-a-helpful-agent-terminal-multiplexer.jsonld"}}