AI agents in a stand-up call

A developer released Agent Standup, a free, open-source tool that turns a Claude Code session into a live stand-up call where a lead agent gives orders and sub-agents join, share their screen and report back at zero token cost. The tool runs as a small local server with entry points for Cursor, Windsurf, VSCodium via a VSIX extension, any terminal, a desktop app, and a Claude Code status line or tmux indicator, and requires Claude Code to have been used on the machine at least once. It offers one status per agent, a context gauge and token counts, replay, recap, tree and video views, voices, custom characters, and 8 languages, and is described by its maker as mostly for fun.

Your AI agents, in a stand-up call. See who is waiting on whom and who is blocked, at zero token cost. Agent Standup turns your Claude Code session into a live team meeting: the lead gives orders, sub-agents join, share their screen and report back. It’s a bit silly. It’s also weirdly useful. An illustration. The real thing is live, has voices, and follows your actual session. It works wherever you run Claude Code. Free · open source See it for real A fictional team in the built-in demo. Use it where you work One small local server, several ways in. Cursor · Windsurf · VSCodium Same extension, installed from the file. Then Install from VSIX… Any terminal No editor needed. Click to copy. Desktop app Its own window and a menu bar indicator. Not signed by Apple. Claude Code status line · tmux A one-line indicator. Details in the README. You need to have used Claude Code on this machine at least once. What you actually get - A live call. - One status per agent. - Sub-agents join, share their screen, leave. - Context gauge and tokens. - Replay, recap, tree, video. - Voices. - Your own characters. - 8 languages. Is it serious? Mostly for fun. No. Made by a bored dev and his robots. ☕ Buy him a coffee https://www.buymeacoffee.com/bored dev and his robots