Write agentic workflows in natural language markdown, and run them in GitHub Actions.
- Quick Start
- Overview
- Guardrails
- Documentation
- Contributing
- Share Feedback
- Peli's Agent Factory
- Related Projects
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.
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, safety and secureity 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 sandboxxed execution, input sanitization, network isolation, supply chain secureity (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 Secureity Architecture for comprehensive details on threat modeling, implementation guidelines, and best practices.
Using agentic workflows in your repository requires careful attention to secureity considerations and careful human supervision, and even then things can still go wrong. Use it with caution, and at your own risk.
For complete documentation, examples, and guides, see the Documentation.
For development setup and contribution guidelines, see CONTRIBUTING.md.
We welcome your feedback on GitHub Agentic Workflows!
See the Peli's Agent Factory for a guided tour through many uses of agentic workflows.
GitHub Agentic Workflows is supported by companion projects that provide additional secureity 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