https://github.com/githubnext/gh-aw
GitHub Agentic Workflows
https://github.com/githubnext/gh-aw
actions cai ci claude-code codex copilot gh-extension github-actions
Last synced: 2 days ago
JSON representation
GitHub Agentic Workflows
- Host: GitHub
- URL: https://github.com/githubnext/gh-aw
- Owner: githubnext
- License: mit
- Created: 2025-08-12T17:40:41.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2026-01-21T01:33:51.000Z (4 days ago)
- Last Synced: 2026-01-21T02:27:18.874Z (4 days ago)
- Topics: actions, cai, ci, claude-code, codex, copilot, gh-extension, github-actions
- Language: Go
- Homepage: https://gh.io/gh-aw
- Size: 355 MB
- Stars: 308
- Watchers: 4
- Forks: 36
- Open Issues: 79
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: CODEOWNERS
- Security: SECURITY.md
- Support: SUPPORT.md
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-gh-extensions - githubnext/gh-aw - 01-18 | GitHub Agentic Workflows | (⭐ Most Starred)
- awesome-continuous-ai - GitHub Agentic Workflows - Framework for creating AI-powered agentic workflows on GitHub (Agentic Frameworks / Continuous Security)
README
# GitHub Agentic Workflows
Write agentic workflows in natural language markdown, and run them in GitHub Actions.
## Contents
- [Quick Start](#quick-start)
- [Overview](#overview)
- [How It Works](#how-it-works)
- [Safe Agentic Workflows](#safe-agentic-workflows)
- [Documentation](#documentation)
- [Contributing](#contributing)
- [Share Feedback](#share-feedback)
- [Agent Factory](#agent-factory)
- [Related Projects](#related-projects)
## Quick Start
Ready to get your first agentic workflow running? Follow our step-by-step [Quick Start Guide](https://githubnext.github.io/gh-aw/setup/quick-start/) 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](https://githubnext.github.io/gh-aw/introduction/how-it-works/).
## How It Works
GitHub Agentic Workflows transforms natural language markdown files into GitHub Actions that are executed by AI agents. Here's an example:
```markdown
---
on:
schedule: daily
permissions:
contents: read
issues: read
pull-requests: read
safe-outputs:
create-issue:
title-prefix: "[team-status] "
labels: [report, daily-status]
close-older-issues: true
---
## Daily Issues Report
Create an upbeat daily status report for the team as a GitHub issue.
```
The `gh aw` cli converts this into a GitHub Actions Workflow (.yml) that runs an AI agent (Copilot, Claude, Codex, ...) in a containerized environment on a schedule or manually.
The AI agent reads your repository context, analyzes issues, generates visualizations, and creates reports - all defined in natural language rather than complex code.
## Safe Agentic Workflows
Security is 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 Guide](https://githubnext.github.io/gh-aw/guides/security/) for comprehensive details on threat modeling, implementation guidelines, and best practices.
> [!WARNING]
> 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](https://githubnext.github.io/gh-aw/).
## Contributing
We welcome contributions to GitHub Agentic Workflows! Here's how you can help:
- **Report bugs and request features** by filing issues in this repository
- **Improve documentation** by contributing to our docs
- **Contribute code** by following our [Development Guide](DEVGUIDE.md)
- **Quick Start**: See [Common Development Tasks](DEVGUIDE.md#common-development-tasks) for scenario-based command reference
- **Share ideas** in the `#continuous-ai` channel in the [GitHub Next Discord](https://gh.io/next-discord)
For development setup and contribution guidelines, see [CONTRIBUTING.md](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 `#continuous-ai` channel in the [GitHub Next Discord](https://gh.io/next-discord).
## Peli's Agent Factory
See the [Peli's Agent Factory](https://githubnext.github.io/gh-aw/blog/2026-01-12-welcome-to-pelis-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)](https://github.com/githubnext/gh-aw-firewall)** - Network egress control for AI agents, providing domain-based access controls and activity logging for secure workflow execution
- **[MCP Gateway](https://github.com/githubnext/gh-aw-mcpg)** - Routes Model Context Protocol (MCP) server calls through a unified HTTP gateway for centralized access management
- **[The Agentics](https://github.com/githubnext/agentics)** - A collection of reusable agentic workflow components, tools, and templates to accelerate workflow development