overstory and multi-agent-shogun

Both tools are **competitors**, offering different approaches to multi-agent orchestration specifically for AI coding agents, with `overstory` emphasizing pluggable runtime adapters for various models and `multi-agent-shogun` focusing on a tmux-based hierarchical orchestration for Claude Code.

overstory
70
Verified
multi-agent-shogun
69
Established
Maintenance 25/25
Adoption 10/25
Maturity 11/25
Community 24/25
Maintenance 23/25
Adoption 10/25
Maturity 11/25
Community 25/25
Stars: 979
Forks: 183
Downloads:
Commits (30d): 329
Language: TypeScript
License: MIT
Stars: 1,046
Forks: 240
Downloads:
Commits (30d): 28
Language: Shell
License: MIT
No Package No Dependents
No Package No Dependents

About overstory

jayminwest/overstory

Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more

Spawns isolated worker agents in git worktrees coordinated via SQLite-backed messaging, merging results through tiered conflict resolution. Supports 11+ pluggable runtimes (Claude Code, Pi, Gemini, Aider, Goose, Amp, etc.) via a unified `AgentRuntime` interface. Includes live TUI dashboards, per-agent inspection, token cost tracking, and explicit warnings about compounding error rates and debugging complexity in multi-agent swarms.

About multi-agent-shogun

yohey-w/multi-agent-shogun

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

Built on bash/tmux as the orchestration layer, the system coordinates up to 8 independent AI CLI agents (Claude Code, OpenAI Codex, GitHub Copilot, or Kimi Code) through disk-based YAML message passing—eliminating coordination API costs entirely. A unified instruction build system generates CLI-specific prompt templates from shared rules, ensuring consistency across heterogeneous agent types. The hierarchy dynamically discovers reusable skill patterns from agent execution logs, promoting validated workflows into persistent commands without manual library curation.

Scores updated daily from GitHub, PyPI, and npm data. How scores work