<div align="center">

multi-agent-shogun

Command your AI army like a feudal warlord.

Run 8 Claude Code agents in parallel — orchestrated through a samurai-inspired hierarchy with zero coordination overhead.

English | 日本語

</div> <p align="center"> <img src="assets/screenshots/tmux_multiagent_9panes.png" alt="multi-agent-shogun: 9 panes running in parallel" width="800"> </p> <p align="center"><i>One Karo (manager) coordinating 8 Ashigaru (workers) — real session, no mock data.</i></p>

---

Give a single command. The Shogun (general) delegates to the Karo (steward), who distributes work across up to 8 Ashigaru (foot soldiers) — all running as independent Claude Code processes in tmux. Communication flows through YAML files and tmux send-keys, meaning zero extra API calls for agent coordination.

<!-- TODO: add demo.gif — record with asciinema or vhs -->

Why Shogun?

Most multi-agent frameworks burn API tokens on coordination. Shogun doesn't.

| | Claude Code Task tool | LangGraph | CrewAI | multi-agent-shogun | |---|---|---|---|---| | Architecture | Subagents inside one process | Graph-based state machine | Role-based agents | Feudal hierarchy via tmux | | | Sequential (one at a time) | Parallel nodes (v0.2+) | Limited | | | | API calls per Task | API + infra (Postgres/Redis) | API + CrewAI platform | (YAML + tmux) | | | Claude logs only | LangSmith integration | OpenTelemetry | + dashboard | | | None | None | None | | | | Built into Claude Code | Heavy (infra required) | pip install | Shell scripts |