Orchestrate complex, multi-step workflows with human-in-the-loop approval, iterative refinement, and quality convergence.
babysitter-explainer.mp4
- What is Babysitter?
- Prerequisites
- Installation
- Quick Start
- How It Works
- Why Babysitter?
- Documentation
- Contributing
- Community and Support
- License
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.
- Node.js: Version 20.0.0+ (22.x LTS recommended)
- Claude Code: Latest version (docs)
- Git: For cloning (optional)
npm install -g @a5c-ai/babysitter@latest @a5c-ai/babysitter-sdk@latest @a5c-ai/babysitter-breakpoints@latestclaude plugin marketplace add a5c-ai/babysitter
claude plugin install --scope user babysitter@a5c.ai
claude plugin enable --scope user babysitter@a5c.aiThen restart Claude Code.
Type /skills in Claude Code to verify "babysit" appears.
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.
+-----------------------------------------------------------------+
| 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.
| 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.
- Process Library - 2,000+ pre-built processes
- Process Definitions
- Quality Convergence
- Run Resumption
- Journal System
- Best Practices
- Architecture Overview
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.
- GitHub Issues: Report bugs or request features
- GitHub Discussions: Ask questions and share ideas
- npm: @a5c-ai/babysitter-sdk
This project is licensed under the MIT License. See LICENSE.md for details.
Built with Claude by A5C AI