🤖 GitHub Agentic Workflows (gh-aw) - GitHub 官方下场 Agent 赛道
GitHub 终于对 Agent 下手了！这是一个允许你用自然语言编写 Agent 工作流的工具，让 GitHub Actions 变得更聪明。
🔍 核心亮点
• 自然语言编排：直接在 issue 中用自然语言描述任务，Agent 自动拆解并执行。
• Action 集成：深度绑定 GitHub Actions，利用现有的生态。
• 安全沙箱：针对 Agent 执行环境做了很多安全加固（这点很关键）。
GitHub Agentic Workflows
Write agentic workflows in natural language markdown, and run them in GitHub Actions.
Contents
- Quick Start
- Overview
- Guardrails
- Documentation
- Contributing
- Share Feedback
- Peli's Agent Factory
- Related Projects
Quick Start
Ready to get your first agentic workflow running? Follow our step-by-step Quick Start Guide to install the extension, add a sample workflow, and see it in action.
Overview
Learn about the concepts behind agentic workflows, explore available workflow types, and understand how AI can automate your repository tasks. See How It Works.
Guardrails
Guardrails, safety and security are foundational to GitHub Agentic Workflows. Workflows run with read-only permissions by default, with write operations only allowed through sanitized safe-outputs. The system implements multiple layers of protection including sandboxed execution, input sanitization, network isolation, supply chain security (SHA-pinned dependencies), tool allow-listing, and compile-time validation. Access can be gated to team members only, with human approval gates for critical operations, ensuring AI agents operate safely within controlled boundaries. See the Security Architecture for comprehensive details on threat modeling, implementation guidelines, and best practices.
Using agentic workflows in your repository requires careful attention to security considerations and careful human supervision, and even then things can still go wrong. Use it with caution, and at your own risk.
Documentation
For complete documentation, examples, and guides, see the Documentation.
Contributing
For development setup and contribution guidelines, see CONTRIBUTING.md.
Share Feedback
We welcome your feedback on GitHub Agentic Workflows! Please file bugs and feature requests as issues in this repository, and share your thoughts in the GitHub Next Discord.
Peli's Agent Factory
See the Peli's Agent Factory for a guided tour through many uses of agentic workflows.
Related Projects
GitHub Agentic Workflows is supported by companion projects that provide additional security and integration capabilities:
- Agent Workflow Firewall (AWF) - Network egress control for AI agents, providing domain-based access controls and activity logging for secure workflow execution
- MCP Gateway - Routes Model Context Protocol (MCP) server calls through a unified HTTP gateway for centralized access management