github/gh-aw

GitHub Agentic Workflows

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 16 minutes ago
Added to GitGenius on February 9th, 2026
Created on August 12th, 2025
Open Issues & Pull Requests: 366 (-9)
Number of forks: 504
Total Stargazers: 4,991 (+0)
Total Subscribers: 42 (+0)

Repository Insights (GitGenius)

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 91% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 12% of tracked open issues have had no activity in three months. Only 12% of issues opened in the past year have been closed. Three people close 98% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 386
New in 7 days: 1,007
Closed in 7 days: 936
Avg open age: 8 days
Stale 30+ days: 111
Stale 90+ days: 49

Recent activity

Opened in 7 days: 856
Closed in 7 days: 827
Comments in 7 days: 1,808
Events in 7 days: 5,102

Top labels

  • automation (8,634)
  • agentic-workflows (6,828)
  • cookie (5,344)
  • testing (3,446)
  • ai-generated (2,032)
  • code-quality (1,710)
  • community (1,139)
  • documentation (1,125)

Most active issues this week

Detailed Description

GitHub Agentic Workflows is a GitHub CLI extension that lets developers define AI-powered repository automation in Markdown with YAML frontmatter and run AI agents securely through GitHub Actions.

The tool addresses the need for intelligent, reasoning-based automation in repositories by letting developers write agentic workflows in a simple Markdown format that the CLI extension compiles into standard GitHub Actions workflows. It complements rather than replaces conventional CI/CD by handling tasks that require reasoning or interpretation—such as issue triage, pull-request review, CI failure investigation, documentation maintenance, dependency analysis, and repository reporting. Agent jobs run read-only and sandboxed by default, with GitHub writes applied through validated safe-outputs jobs that use scoped permissions to maintain security boundaries.

Developers should choose this tool when they need AI-assisted automation for tasks requiring judgment rather than deterministic execution. It suits repositories where teams want to leverage AI reasoning without building custom integrations. The tool supports multiple AI engines including GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, and Pi, so teams can select based on their existing tooling and preferences. Installation requires no GitHub token, and setup involves selecting an engine and running the init command to configure the repository.

Almost all open issues are raised by outside users rather than by the core team, indicating a substantial base of adopters reporting real-world use.