Skip to content

Benihakak/babysitter

 
 

Repository files navigation

Babysitter

https://a5c.ai


npm version License: MIT GitHub issues GitHub stars

Orchestrate complex, multi-step workflows with human-in-the-loop approval, iterative refinement, and quality convergence.

Getting Started | Documentation | Community


babysitter-explainer.mp4

Table of Contents


What is Babysitter?

Babysitter is an orchestration framework for Claude Code that enables deterministic, event-sourced workflow management. It allows you to build complex, multi-step development processes with built-in quality gates, human approval checkpoints, and automatic iteration until quality targets are met. Babysitter works seamlessly with your existing subagents, skills, and tools, orchestrating them into sophisticated workflows.


Prerequisites

  • Node.js: Version 20.0.0+ (22.x LTS recommended)
  • Claude Code: Latest version (docs)
  • Git: For cloning (optional)

Installation

1. Install the SDK

npm install -g @a5c-ai/babysitter@latest @a5c-ai/babysitter-sdk@latest @a5c-ai/babysitter-breakpoints@latest

2. Install the Plugin

claude plugin marketplace add a5c-ai/babysitter
claude plugin install --scope user babysitter@a5c.ai
claude plugin enable --scope user babysitter@a5c.ai

Then restart Claude Code.

3. Verify Installation

Type /skills in Claude Code to verify "babysit" appears.


Quick Start

claude "/babysitter:call implement user authentication with TDD"

Or in natural language:

Use the babysitter skill to implement user authentication with TDD

Claude will create an orchestration run, execute tasks step-by-step, handle quality checks and approvals, and continue until completion.


How It Works

+-----------------------------------------------------------------+
|                     Babysitter Loop                              |
|                                                                  |
|   +----------+     +----------+     +----------+     +----------+|
|   | Iterate  | --> |   Get    | --> | Execute  | --> |   Post   ||
|   |          |     | Effects  |     |  Tasks   |     | Results  ||
|   +----------+     +----------+     +----------+     +----------+|
|        |                                               |         |
|        +----------------- repeat <---------------------+         |
+-----------------------------------------------------------------+

Each iteration: Advance process -> Get pending effects -> Execute tasks -> Record outcomes -> Repeat until complete.

Everything is recorded: .a5c/runs/<runId>/ contains journal, tasks, and state. Pause, resume, or recover at any point.


Why Babysitter?

Traditional Approach Babysitter
Run script once, hope it works Iterate until quality target met
Manual approval via chat Structured breakpoints with context
State lost on session end Event-sourced, fully resumable
Single task execution Parallel execution, dependencies
No audit trail Complete journal of all events
Fixed workflow Process-driven, customizable

Key differentiators: Deterministic replay, quality convergence, human-in-the-loop breakpoints, agent scoring, and parallel execution.


Documentation

Getting Started

Features

Reference


Contributing

We welcome contributions! Here's how you can help:

  • Report bugs: GitHub Issues
  • Suggest features: Share your ideas for improvements
  • Submit pull requests: Fix bugs or add features
  • Improve documentation: Help make docs clearer

See CONTRIBUTING.md for detailed guidelines.


Community and Support

Star History

Star History Chart

Contributors


License

This project is licensed under the MIT License. See LICENSE.md for details.


Built with Claude by A5C AI

Back to Top

About

Babysitter enables Claude Code to manage extremely complex tasks through deterministic, hallucination-free self-orchestration

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages

  • JavaScript 96.3%
  • TypeScript 3.4%
  • Shell 0.2%
  • CSS 0.1%
  • Python 0.0%
  • HTML 0.0%