# GitHub Agentic Workflows

> MIT gh extension — Markdown agent jobs compiled to Actions with safe outputs

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://github.github.com/gh-aw/  
**GitHub:** https://github.com/github/gh-aw  
**Added:** 2026-10-05

---

## The Hook

GitHub Agentic Workflows (`gh-aw`) lets you write repo automation as Markdown with YAML frontmatter — issue triage, PR review, CI-failure investigation, docs upkeep — and compiles it into a normal GitHub Actions workflow where the agent runs read-only and sandboxed.

## What's Good

MIT (github/gh-aw, latest v0.89.21). `gh extension install github/gh-aw`; `gh aw compile` validates the source and emits a `.lock.yml`. Engines: GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, Pi. Writes go through validated `safe-outputs` jobs with scoped permissions instead of giving the agent a write token. Ships agent-readable docs (llms.txt, llms-full.txt). ★~5.3k.

## The Catch

Maturity: pre-1.0 and the README itself says use with caution at your own risk; releases `>=0.83.3 <0.85.4` were retired after a security advisory — pin a current version. Cost is real: every run spends Actions minutes plus your engine’s tokens/seat. Permissions, tools, and network access are configurable, so a careless frontmatter undoes the sandbox. Vs claude-code-action: that runs Claude Code on PR/issue events; gh-aw is a multi-engine workflow compiler with a write-buffer safety model.

## Verdict

MIT agentic GitHub Actions when you want triage/review/CI-investigation bots with read-only agents and buffered writes — pin versions and budget minutes plus tokens.