by qingni · Codex Skill · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
AgentCrew 一个面向 macOS 的万物编排工作台（Universal CLI Orchestration Workbench） 不仅能将 Codex、Claude、Cursor-Agent 等多种 AI 工具无缝组织成可视化工作流，还能混合编排任意传统 CLI 命令（如 git、npm、docker、ffmpeg 等），在本地完成研发、测试、部署与自动化运维的完整闭环。 简体中文 | English ✨ 核心亮点 (Key Features) AgentCrew 并非要替代某一个具体的 AI 聊天工具，而是提供一个统一的 Orchestration Layer，让多种 AI CLI 能以更稳定、可复用、可观察的方式协作。 💻 极致的 macOS 原生体验 基于 SwiftUI 构建，运行轻量、流畅。 可视化 Flowchart、全链路执行监控、本地系统通知。 🔄 独创双引擎驱动：Pipeline 与 Agent 模式并存 同一任务可自由在两种模式间切换，兼顾执行效率与智能闭环： ⚡️ Pipeline 模式：基于静态 DAG 工作流，执行路径极短。适合目标明确、步骤固定、追求速度与成本控制的标准化任务。 🧠 Agent 模式：基于多轮动态执行（Plan - Execute - Evaluate - Replan）。支持自动诊断失败原因、自动补齐修复步骤，并在高风险操作前（如删
| Stars | 52 |
| Forks | 14 |
| Language | Swift |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 63.5456285757884/100 |
| Last Updated | 2026-04-15 |
| Created | 2026-03-11 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~267k |
Looking for a AgentCrew alternative? If you're comparing AgentCrew with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agent harness for codebases. Gives Claude Code, Codex, and CI a shared task system, verdict ledger, and state
Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 30 regions. Sema
Claude Code context engineering & planning system for individual AI development workflows
Personal Assistant Wizard for Claude Code — npx pawmode
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Verified agent runtime for Kimi Code. Stable daily-use core with alpha orchestration surfaces; release-gated a
Explore other popular codex skill tools:
AgentCrew is A universal orchestration workbench for macOS. Seamlessly mix AI models (Codex, Claude) with traditional CLI tools (git, npm) via static DAG pipelines or dynamic self-healing agents, creating a fully . It is categorized as a Codex Skill with 52 GitHub stars.
AgentCrew is primarily written in Swift. It covers topics such as ai-agents, automation, cli.
You can find installation instructions and usage details in the AgentCrew GitHub repository at github.com/qingni/AgentCrew. The project has 52 stars and 14 forks, indicating an active community.
AgentCrew is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to AgentCrew on Agent Skills Hub include maestro, OpenConstructionEstimate-DDC-CWICR, ContextKit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.