overstory and claude-tmux-orchestration

While both tools facilitate multi-agent orchestration for AI coding, the first project offers a broader, pluggable runtime adapter framework for various large language models, making it a more general solution, whereas the second is a specialized orchestration system specifically designed for Claude Code within a tmux environment, suggesting the latter could be used as a specific implementation or example within the ecosystem of the former.

overstory
70
Verified
claude-tmux-orchestration
28
Experimental
Maintenance 25/25
Adoption 10/25
Maturity 11/25
Community 24/25
Maintenance 13/25
Adoption 6/25
Maturity 9/25
Community 0/25
Stars: 979
Forks: 183
Downloads:
Commits (30d): 329
Language: TypeScript
License: MIT
Stars: 21
Forks:
Downloads:
Commits (30d): 0
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 claude-tmux-orchestration

primeline-ai/claude-tmux-orchestration

Claude Code tmux orchestration — spawn full AI sessions as parallel workers with heartbeat monitoring and file-based coordination

Spawns independent Claude Code instances in tmux windows, each with full 1M context and tool access, coordinated through JSON state files and bash heartbeat polling. Uses file-based escalation (no IPC) and adaptive sleep intervals to detect idle states before injecting orchestration commands via `tmux send-keys`. Integrates directly with the Claude Code CLI, targeting teams automating parallel research, code generation, or review workflows within a single tmux session.

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