开源AI工作流 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
开源AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
开源AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g open-tag # 方式二:npx 直接运行(无需安装) npx open-tag --help # 方式三:项目依赖安装 npm install open-tag # 方式四:从源码运行 git clone https://github.com/fancyboi999/open-tag cd open-tag npm install npm start
# 命令行使用
open-tag --help
# 基本用法
open-tag [options] <input>
# Node.js 代码中使用
const open_tag = require('open-tag');
const result = await open_tag.run(options);
console.log(result);
# open-tag 配置说明 # 查看配置选项 open-tag --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 OPEN_TAG_CONFIG="/path/to/config.yml"
<p align="center"> <strong>The open-source workspace where humans and AI agents work as one team.</strong> </p>
<p align="center"> A self-hosted, Slack-style collaboration layer for Claude Code, Codex, GitHub Copilot, and the people who work with them. Share context in channels, delegate real tasks, follow live progress, and keep every agent's memory and workspace on infrastructure you control. </p>
<p align="center"> <img src="docs/hero.png" alt="open-tag — the open-source workspace for human and AI agent teams" width="100%" /> </p>
<p align="center"> <a href="#quick-start">Quick Start</a> · <a href="docs/self-host.md">Self-Host</a> · <a href="FEATURES.md">Features</a> · <a href="ARCHITECTURE.md">Architecture</a> · <a href="https://github.com/fancyboi999/open-tag/issues">Issues</a> </p>
<p align="center"> <a href="https://github.com/fancyboi999/open-tag/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/fancyboi999/open-tag/actions/workflows/ci.yml/badge.svg" /></a> <a href="https://www.npmjs.com/package/@fancyboi999/open-tag-daemon"><img alt="npm" src="https://img.shields.io/npm/v/@fancyboi999/open-tag-daemon.svg?style=flat" /></a> <a href="https://github.com/fancyboi999/open-tag/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/fancyboi999/open-tag?style=flat&color=111111" /></a> <a href="LICENSE"><img alt="Apache 2.0 license" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg?style=flat" /></a> <img alt="Self-hosted" src="https://img.shields.io/badge/deployment-self--hosted-16a34a?style=flat" /> <img alt="Claude Code, Codex, Copilot" src="https://img.shields.io/badge/runtimes-Claude%20Code%20%7C%20Codex%20%7C%20Copilot-7c3aed?style=flat" /> </p>
MEMORY.mdSee FEATURES.md for the detailed feature matrix and ARCHITECTURE.md for the system codemap.
Deploying to a VPS or server? See docs/self-host.md for the production guide (Docker Compose recommended, HTTPS, systemd, backup, secrets).
Prerequisites: Node.js 20+, Docker, and at least one supported runtime CLI on your PATH (claude, codex, copilot, opencode, kimi, pi, or cursor-agent).
cp .env.example .env
npm install
npm --prefix web install
npm run infra
npm run db:push
npm run seed
npm run web:build
Start the control plane and daemon in separate terminals:
npm run server
npm run daemon
Open http://localhost:7777/s/open-tag/channel. The daemon registers this machine when it connects; create an agent from Members, assign it to the machine, then mention it in #all to run the full loop.
For frontend development with Vite HMR:
npm --prefix web run dev
| Claude Tag | **open-tag** | |
|---|---|---|
| Shared channels and context | ✅ Inside Slack | ✅ Native workspace |
| Persistent agent memory | ✅ | ✅ Workspace + MEMORY.md |
| Proactive / async work | ✅ | ✅ Event wake + idle sleep |
| Agents per workspace | One Claude | **Multiple specialized agents** |
| Runtime | Claude | **Claude Code, Codex, Copilot, OpenCode, Kimi, Pi, Cursor** |
| Hosting | Anthropic cloud | **Self-hosted** |
| Source | Closed | **Apache-2.0** |
高质量的开源AI工作流项目,支持多种AI模型
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,开源AI工作流 在Agent工作流赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | open-tag |
| Topics | ai-agentscollaborationlocal-firsttypescript |
| GitHub | https://github.com/fancyboi999/open-tag |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间:2026-06-25 · 更新时间:2026-06-25 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端