ralph-eats-beads

Orchestrate Claude agents to execute bd tasks in parallel tmux subwindows.

2|1|Updated Jan 16, 2026

Search Tags:#automation #AI agents #Claude #parallel execution #tmux #bd beads

Ready to run

npx skills add https://github.com/rawwerks/ralph-eats-beads --skill ralph-eats-beads

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ralph-eats-beads
Source: https://github.com/rawwerks/ralph-eats-beads/tree/main
Command: npx skills add https://github.com/rawwerks/ralph-eats-beads --skill ralph-eats-beads

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bd, tmux, claude, git, and includes scripts (resource) components.

What problem does it solve?

This skill automates an autonomous coding loop by orchestrating Claude agents that pull tasks from bd ready and execute them in parallel tmux subwindows.

Core Features & Use Cases

Parallel execution: Spawns multiple subagents to work on separate bd issues in parallel, improving throughput.
Plan-driven workflow: Aligns with bd epics and issues, automatically syncing progress and closing tasks when done.
Observability: Uses tmux windows for real-time visibility into each subagent's progress and results.
Use Case: In a project with many bd-ready tasks, start Ralph to orchestrate 3-5 subagents across tmux windows, each implementing a single issue, then aggregate results automatically.

Quick Start

Ensure bd is initialized with an epic and initial issues.
Generate a plan: scripts/planner.sh requirements.md or create issues manually.
Start the implementation loop: scripts/ralph.sh 25

Frequently Asked Questions about ralph-eats-beads

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate parallel execution of AI coding agents in tmux?▼

You can automate an autonomous coding loop by orchestrating Claude agents that pull tasks from bd ready and execute them in parallel tmux subwindows. This allows multiple subagents to work on different issues simultaneously, improving throughput.

How do I set up an autonomous AI loop to ship features overnight?▼

To set up an autonomous AI loop, initialize bd with an epic and initial issues, generate a plan with scripts/planner.sh, and start the loop with scripts/ralph.sh. The spawned subagents automatically sync progress and close bd tasks upon successful implementation.

Do I need the bd tool and Claude CLI to run parallel AI agents?▼

Yes, running parallel AI agents requires the bd tool, tmux, and Claude CLI. These dependencies are essential because bd provides the tasks, tmux manages parallel subwindows, and Claude CLI executes the coding work.

What is the best way to monitor parallel AI agents working on separate tasks?▼

The best way to monitor parallel AI agents is using tmux windows for real-time visibility into each subagent's progress. Additionally, a watchdog script monitors spawned subagents to handle stalled work and ensure continuous progress across all active tasks.

How does the watchdog handle stalled work in an autonomous coding loop?▼

The watchdog handles stalled work by monitoring spawned Claude subagents in tmux and intervening to ensure progress. It synchronizes parallel work across subwindows to prevent bottlenecks and keep the autonomous coding loop running continuously.

Can I use Claude CLI for plan-driven development with bd epics and issues?▼

Yes, you can use Claude CLI for plan-driven development with bd epics and issues. The autonomous coding loop aligns subagents with bd tasks, automatically syncing progress and closing issues when implementation succeeds.