#705 · Primary category: AI Agents & Automation

multi-agent-shogun

ai-agent anthropic automation claude-code llm multi-agent parallel-processing samurai shogun tmux

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

Project last updated:08/06/26

GitHub Stars

1.4K

Forks

292

Contributors

17

License

MIT

Why we included this project

Anyone running more than one or two coding-agent sessions at once knows how fast it gets hard to tell which terminal is working on what. multi-agent-shogun tackles that directly with tmux: it launches several instances of tools like Claude Code or Codex into separate panes and organizes them through a simple shogun → karo → ashigaru hierarchy. One coordinating pane hands tasks down to worker agents while a strategist pane keeps an eye on the whole operation. The appeal is less about clever AI internals and more about honest process orchestration, with a hands-free voice mode for dictating tasks as you go. Solo developers and small teams who want to spread a big refactor or a batch of tickets across parallel agents, without building their own tmux wrapper, will find it pragmatic and quick to set up. You do need tmux and a supported agent CLI installed first, but the setup script makes the rest straightforward.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category