OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Multi Agent Shogun

Multi Agent Shogun is a Shell/Bash developer tool that orchestrates parallel AI coding CLI sessions through tmux and a Shogun–Karo–Ashigaru hierarchy. It uses YAML files for agent coordination and provides visible terminal panes and a dashboard for monitoring work.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Multi Agent Shogun — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a software task can be divided into concurrent assignments and you want to manage them from a terminal-based hierarchy.

Who it is for

  • Developers who use AI coding CLIs and want to distribute a coding task across parallel agents.
  • CLI users who want to observe agent instructions and progress in tmux panes.

Documented uses

  • Delegate a coding request through a manager role to multiple worker agents.
  • Run independent AI coding sessions in parallel.
  • Monitor agent activity through tmux panes and a dashboard.
Before you choose

Requirements & limits

The project is a public GitHub repository under the MIT license. Its documented setup requires a local Linux environment or WSL2 on Windows, tmux, Bash 4 or later, and at least one supported coding CLI.

  • The orchestration layer is Shell/Bash and tmux, with YAML-file communication.
  • The README names Claude Code, OpenAI Codex, GitHub Copilot, Kimi Code, OpenCode, Cursor and Antigravity as supported CLIs.
  • The documented quick-start flow describes seven worker agents and one strategist, while the README also uses a broader ten-agent description.
  • On Windows, the documented route depends on WSL2 and Ubuntu.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and launch Multi Agent Shogun on Linux

Prepare the repository and start the agent system using the documented Bash setup.

Before you start

  • tmux
  • Bash 4 or later
  • At least one supported coding CLI: Claude Code, Codex, Copilot, Kimi, OpenCode or Antigravity
  • A cloned copy of the repository

Steps

  1. Clone the repository and change into its directory.

  2. Run the command below for one-time configuration, dependencies and MCP setup.

    Documented command
    bash first_setup.sh

  3. Run source ~/.bashrc to reload the PATH changes.

  4. For Claude Code, complete the documented first-run OAuth and permissions prompt, then exit the CLI.

  5. Run the command below to launch the agents.

    Documented command
    bash shutsujin_departure.sh

Expected outcome

The Shogun system launches its agent sessions for parallel coding work, which can be directed from the Shogun pane.

Guide limitations

  • The guide documents a first-run authentication flow specifically for Claude Code; other CLI authentication steps are not detailed here.
  • The README notes a Windows route using WSL2 and Ubuntu rather than native Windows execution.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Multi Agent ShogunDelegate a coding request through a manager role to multiple worker agents.CLIThe project is a public GitHub repository under the MIT license. Its documented setup requires a local Linux environment or WSL2 on Windows, tmux, Bash 4 or later, and at least one supported coding CLI.
MassgenRun multiple AI agents against the same user task.CLIThe repository documents installation through pip or uv and requires Python 3.11 or later. Setup can configure API keys for OpenAI, Anthropic, Google and xAI; credentials are needed for the selected model backends.
Langchain Multi Agents BoilerplateRoute incoming football questions to model and agent workflows according to task complexity.WebThe repository is public and specifies an MIT license. Running the application requires OpenAI and Groq API keys and a Redis server.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
yohey-w/multi-agent-shogun · Official homepage title · retained in its source language
How we review sourcesSuggest a correction