Show HN: A lightweight way to make agents talk without paying for API usage

dragonfax 3 hours ago | parent | next [-]

Claude Code (subscription) has Agent Teams built in. Teams of Agents communicate with local files that they use as inboxes and task list. Has tmux and iTerm 2 integration. https://code.claude.com/docs/en/agent-teams

They can rack up some extra tokens if you leave agents going idle. Because they loop, checking for new messages for them.

This fellow reverse-engineered exactly how it works and then abstracted the pattern into an MCP server that any Harness/agent can use. https://github.com/cs50victor/claude-code-teams-mcp

▲

scalefirst 3 hours ago | parent | prev | next [-]

Have you seen https://www.roborev.io/ from Wes McKinney?

	▲	perelin an hour ago \| parent [-]
		Any personal experience with it? Recommended?

▲

swingboy 4 hours ago | parent | prev | next [-]

I put together a skill to do this with OpenCode and the GitHub Copilot provider. Works pretty well.

▲

pitched 4 hours ago | parent | prev [-]

I’ve been keeping them open in tmux and using either send_keys or paste buffer for communication. Using print mode and always resume last means you can’t have parallel systems going.