AI工作流协调 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
AI工作流协调 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。
AI工作流协调 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:cargo install(推荐) cargo install agentscommander # 方式二:从源码编译 git clone https://github.com/mblua/AgentsCommander cd AgentsCommander cargo build --release # 二进制在 ./target/release/agentscommander
# 查看帮助 agentscommander --help # 基本运行 agentscommander [options] <input> # 详细使用说明请查阅文档 # https://github.com/mblua/AgentsCommander
# agentscommander 配置说明 # 查看配置选项 agentscommander --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 AGENTSCOMMANDER_CONFIG="/path/to/config.yml"
<p align="center"> <img src="src-tauri/icons/icon.png" width="160" alt="Agents Commander logo" /> </p>
<p align="center"> Run multiple teams of AI coding agents (Claude Code, Codex, Gemini) across separate workgroup instances.<br/> Root Agent coordination, visible terminals, and file-based workflows you can inspect. </p>
<p align="center"> <a href="https://github.com/mblua/AgentsCommander/releases/latest"><img src="https://img.shields.io/github/v/release/mblua/AgentsCommander?style=flat-square&color=00d4ff&label=release" alt="GitHub release" /></a> <a href="https://github.com/mblua/AgentsCommander/actions/workflows/release.yml"><img src="https://img.shields.io/github/actions/workflow/status/mblua/AgentsCommander/release.yml?style=flat-square&label=build" alt="Build" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License: MIT" /></a> <a href="https://github.com/mblua/AgentsCommander/stargazers"><img src="https://img.shields.io/github/stars/mblua/AgentsCommander?style=flat-square&color=00d4ff&label=stars" alt="GitHub stars" /></a> <a href="CODE_SIGNING_POLICY.md"><img src="https://img.shields.io/badge/code--signed-SignPath-00d4ff?style=flat-square&logo=windows" alt="Code-signed · SignPath" /></a> <a href="https://tauri.app"><img src="https://img.shields.io/badge/built%20with-Rust%20%2B%20Tauri%202-dea584?style=flat-square&logo=rust" alt="Built with Rust + Tauri 2" /></a> </p>
<p align="center"> <a href="https://github.com/mblua/AgentsCommander/releases/latest"><b>⬇ Download (latest release)</b></a> · <a href="#60-second-quickstart"><b>▶ 60-second quickstart</b></a> · <a href="docs/quickstart.md"><b>Quickstart</b></a> </p>
---
| Use case | Setup |
|---|---|
| **Parallel feature development** | Two coding agents on the same repo, each owning a different module. Coordinator routes work and merges results. |
| **Code-review swarm** | One agent ships a PR; two others review independently. You read both reviews in their own terminals before merging. |
| **Autonomous refactor crew** | A long-running coordinator splits a multi-file refactor across worker agents and rebases their branches as they finish. |
| **Long-running agent with phone alerts** | Pair a session with a [Telegram bot](docs/features/telegram-bridge.md), kick off a build from your phone, and receive text updates plus screenshots or image artifacts. |
Full recipes: docs/use-cases.md.
.exe, Linux .AppImage, and macOS .dmg are built on every release..exe directly; see Portable instances).New Project in the sidebar and point it at an empty folder. AC creates an .ac/ workspace there. Existing .ac-new/ projects still open as legacy projects.Full walkthrough: docs/quickstart.md.
| AgentsCommander | LangGraph | AutoGen / AG2 | CrewAI | Aider | Claude Code alone | |
|---|---|---|---|---|---|---|
| **Operates real CLI coding agents** | ✅ Claude Code, Codex, Gemini | ❌ Python LLM calls | ❌ Python conversation | ❌ Python library | Partial (one agent) | ✅ (one agent) |
| **Real PTY per agent** | ✅ ConPTY / Unix PTY | ❌ | ❌ | ❌ | ✅ | ✅ |
| **Filesystem-first messaging** | ✅ Markdown in messaging/ | ❌ DB / Python state | ❌ Python objects | ❌ Python tasks | n/a | n/a |
| **Standalone runtime** | ✅ Rust / Tauri | ❌ Python library | ❌ Python library | ❌ Python library | ❌ Python app | ✅ standalone CLI |
| **Multi-agent on the same repo** | ✅ | Partial | Partial | Partial | ❌ | ❌ |
| **Desktop UI** | ✅ Tauri app | ❌ | ❌ | ❌ | TUI only | TUI only |
Full comparison with trade-offs and honest losses: docs/comparison.md.
高质量的AI工作流协调工具
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。
经综合评估,AI工作流协调 在Agent工作流赛道中表现稳健,质量良好。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 | AgentsCommander |
| 原始描述 | 开源AI工作流:Coordinate multiple teams of AI coding agents across workgroup instances with Ro。⭐6 · Rust |
| Topics | AI工作流Rust开发工具 |
| GitHub | https://github.com/mblua/AgentsCommander |
| License | MIT |
| 语言 | Rust |
收录时间:2026-05-31 · 更新时间:2026-06-02 · License:MIT · 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