GitHub Agentic Workflows

Active

Description

Official GitHub CLI extension for Agentic Workflows, enabling definition and execution of AI agent workflows within the GitHub ecosystem for automated code reviews, issue handling, and more.

Key Features

Write agentic workflows in natural language Markdown without complex configuration
Deep integration with GitHub Actions for running AI workflows directly in CI/CD
Multi-layer safety guardrails: read-only by default, writes via sanitized safe-outputs
Support for multiple AI models: GitHub Copilot, Claude, Codex, and Gemini
Sandboxed execution with input sanitization and network isolation
Compile-time validation with team access controls and human approval gates

Use Cases

💡 Automated code reviews and Pull Request management

💡 Automatic Issue triage, priority sorting, and intelligent assignment

💡 Context-aware automated documentation generation from repository content

💡 Security scanning and compliance checks within continuous integration

💡 Automated notifications and status synchronization for team collaboration

Strengths & Limitations

✅ Strengths

• Actively maintained, recent updates
• High community interest (5.1k stars)
• Permissive open-source license (MIT)

⚠️ Limitations

• High issue backlog (448 open issues)

Quick Start

Install the GitHub CLI extension, create a Markdown file defining your workflow, and run it with the gh aw command. Workflows use natural language to describe task goals, executed by AI models within the GitHub Actions environment.

Visit GitHub

Related Projects

Flyte

7.4k · Go

Active A

Dynamic, resilient AI orchestration platform. Coordinate data, models, and compute as you build AI workflows with scalable ML pipeline and production-grade workload management.

goworkflowautomation +2

· Pure Python declarative orchestration — define workflows with @task decorators, no YAML or DSL needed
· Elastic scaling and fault tolerance — auto-retry, timeout management, distributed parallel execution
· Model serving built-in — FastAPIAppEnvironment deploys REST APIs with one line of code

View full details → View on GitHub

1Panel

36.8k · Go

Active A+

A modern open-source VPS control panel with native AI agent support, enabling Ollama model deployment, AI agent management and full server stack control.

devopsgoagent +2

· AI agent runtime — Built-in Ollama LLM and OpenClaw agent deployment with GPU monitoring
· One-click website deployment — Auto domain binding, SSL provisioning, and Nginx config with zero manual setup
· App marketplace — 165+ trusted open-source apps (Nextcloud, Bitwarden, etc.) installed with one click

View full details → View on GitHub

Patchwork

1.6k · Python

Active B

Agentic AI framework for enterprise workflow automation. Uses LLM-powered pipelines for code reviews, DevOps, and other enterprise tasks.

automationworkflowagent +2

· Reusable atomic Steps for creating PRs, committing changes, calling LLMs, and more
· Customizable Prompt Templates optimized for library updates, code generation, and vulnerability remediation
· Patchflows combining Steps and Prompts for PR reviews, code fixing, and documentation automation

View on GitHub

Integuru

4.8k · Python

Normal A

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs for cross-platform automation.

workflowpythonagent +2

· Automated reverse engineering of platform internal APIs through browser network request analysis
· Dependency graph generation for complex API request chains and authentication flows
· Runnable Python code generation that hits internal endpoints to perform desired actions