AI Skill Hub 强烈推荐:babysitter AI工具 是一款优质的AI工具。AI 综合评分 8.2 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
Claude开源技能,用于智能体编排和工作流管理。通过实现对agentic AI的约束和控制机制,帮助开发者构建可靠的多智能体系统,适合需要精细化控制和协调多个AI代理的企业和开发团队。
babysitter AI工具 是一款基于 JavaScript 开发的开源工具,专注于 Claude技能、智能体编排、智能体协调 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
Claude开源技能,用于智能体编排和工作流管理。通过实现对agentic AI的约束和控制机制,帮助开发者构建可靠的多智能体系统,适合需要精细化控制和协调多个AI代理的企业和开发团队。
babysitter AI工具 是一款基于 JavaScript 开发的开源工具,专注于 Claude技能、智能体编排、智能体协调 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:npm 全局安装 npm install -g babysitter # 方式二:npx 直接运行(无需安装) npx babysitter --help # 方式三:项目依赖安装 npm install babysitter # 方式四:从源码运行 git clone https://github.com/a5c-ai/babysitter cd babysitter npm install npm start
# 命令行使用
babysitter --help
# 基本用法
babysitter [options] <input>
# Node.js 代码中使用
const babysitter = require('babysitter');
const result = await babysitter.run(options);
console.log(result);
# babysitter 配置说明 # 查看配置选项 babysitter --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export BABYSITTER_CONFIG="/path/to/config.yml"
---
Babysitter supports multiple AI coding harnesses. Install the plugin for your harness of choice:
/babysitter:doctor
Run diagnostics to confirm everything is working.
---
babysitter harness:discover
babysitter harness:install claude-code
babysitter harness:install-plugin claude-code ```
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:user-install
This creates your personal profile with: - Breakpoint preferences (how much oversight you want) - Tool preferences and communication style - Expertise areas for better process matching
babysitter compression:config ```
Edit .a5c/compression.config.json to persist settings (env vars always take priority):
{
"enabled": true,
"layers": {
"userPromptHook": { "enabled": true, "threshold": 500, "keepRatio": 0.78 },
"commandOutputHook": { "enabled": true, "excludeCommands": ["jq", "curl", "docker"] },
"sdkContextHook": { "enabled": true, "targetReduction": 0.15, "minCompressionTokens": 150 },
"processLibraryCache": { "enabled": true, "targetReduction": 0.35, "ttlHours": 24 }
}
}
Toggle any layer with babysitter compression:toggle <layer> <on|off> or set individual values with babysitter compression:set <key> <value>.
---
After cloning this repo, From within the Codex CLI:
codex
> /plugins
Navigate to the "babysitter" entry and select "Install".
Via the Cursor marketplace or npm:
npm install -g @a5c-ai/babysitter-cursor
npm install -g @a5c-ai/babysitter-gemini
babysitter-gemini install --global
Beyond the in-session skill commands (/babysitter:call, etc.), the Babysitter SDK provides harness:* CLI commands that let you create, run, and manage orchestration sessions from the terminal. These commands work with any installed harness.
---
Babysitter has its own plugin system -- and it works differently from what you might expect. A babysitter plugin is not a code module with extension points. It's a set of natural language instructions (markdown files) or deterministic coded processes (JS files) that an AI agent reads and executes. The SDK stores, versions, and distributes the instructions. The AI agent is the runtime.
This means a plugin can do anything an AI agent can do: install npm packages, generate CI/CD pipelines, set up git hooks, create Terraform configs, modify your linter rules, copy babysitter processes into your project, and interview you about your preferences along the way.
The official marketplace includes plugins for security (gitleaks, ESLint security rules, audit processes), testing (Vitest/Playwright/pytest setup, coverage gates, TDD processes), deployment (Terraform, Helm, Dockerfiles, multi-environment pipelines), themes (sound effects, design systems, conversational personality), CI/CD (GitHub Actions workflows), and rate limiting (exponential backoff hooks).
To manage plugins, use the /babysitter:plugins command inside your harness (or babysitter harness:plugins from the CLI). The agent reads the plugin's install instructions, interviews you, analyzes your project, and executes the setup -- all within a babysitter orchestration run.
See the full Plugins documentation for details on how installs work, the marketplace format, creating your own plugins, and the migration system.
---
babysitter harness:call \ --harness internal \ --process .a5c/processes/lint-and-test.js#process \ --workspace . \ --no-interactive \ --json ```
It executes processes using the SDK's built-in engine, supports all effect types (tasks, breakpoints, sleeps, parallel dispatch), and produces the same event-sourced journal as any other harness.
---
本项目为 Babysitter 项目的简介,介绍了该项目的基本信息和目的。
本节介绍了 Babysitter 项目的主要功能,包括 Process Library、Process Definitions、Quality Convergence、Run Resumption、Journal System 和 Best Practices 等。
本节列出了 Babysitter 项目的环境依赖和系统要求,包括 Node.js、Claude Code 和 Git 等。
本节提供了安装 Babysitter 项目的步骤,包括支持多种 AI 编码 harness 的安装和配置。
本节提供了使用 Babysitter 项目的快速入门指南,包括使用 Claude CLI 和 natural language 指令等。
本节介绍了配置 Babysitter 项目的方法,包括配置个人资料、设置断点偏好和工具偏好等。
本节介绍了 Babysitter 项目的 API 接口,包括 Codex CLI、Cursor IDE 和 CLI、Gemini CLI 等。
本节介绍了 Babysitter 项目的工作流和模块,包括插件系统和使用 Babysitter 的示例代码等。
aiskill88点评:成熟的智能体编排方案,783星标表明社区认可度高。解决了多agent系统的协调难题,代码质量可靠,文档完善,值得部署。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,babysitter AI工具 是一款质量优秀的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | babysitter |
| 原始描述 | 开源Claude技能:Babysitter enforces obedience on agentic workforces and enables them to manage e。⭐783 · JavaScript |
| Topics | Claude技能智能体编排智能体协调工作流管理JavaScript |
| GitHub | https://github.com/a5c-ai/babysitter |
| License | MIT |
| 语言 | JavaScript |
收录时间:2026-05-14 · 更新时间:2026-05-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。