ferry vs gh-aw
AI-powered repository automation compared
ferry and gh-aw both use AI agents in GitHub Actions to automate repository work. ferry starts a staged development pipeline from Jira ticket transitions, while gh-aw lets teams define a broader range of repository tasks in Markdown workflows.
ferry: Turn Jira Ticket Moves Into Draft Pull Requests
Ferry uses Jira ticket transitions to start an agent pipeline in GitHub Actions, from refinement through review and merging. It suits teams seeking an automated development workflow, but requires Jira Cloud, GitHub Actions setup, and an LLM provider.
gh-aw: Define AI Workflows for GitHub Actions
GitHub Agentic Workflows is a Go-based GitHub CLI extension for defining AI-powered repository automation in Markdown and running it through GitHub Actions. It compiles workflows for supported agents, with read-only defaults and controlled write jobs.
| ferry | gh-aw | |
|---|---|---|
| Language | TypeScript | Go |
| License | MIT | MIT |
| Stars | 3 | 5.4k |
| Forks | 1 | 596 |
| Last analyzed | Oct 4, 2026 | Oct 23, 2026 |
Key differences
- ferry is centered on Jira-triggered work from refinement through development, review, and merging; gh-aw supports tasks such as issue triage, pull-request review, and CI investigation.
- ferry offers a local runner with per-ticket worktrees and describes GitLab CI support as experimental; gh-aw compiles Markdown workflow definitions into GitHub Actions workflows.
- ferry is written in TypeScript and requires Jira Cloud and Node.js 20 or newer; gh-aw is written in Go and is a GitHub CLI extension.
- ferry separates work among named agent phases; gh-aw supports several AI engines, including Copilot, Claude Code, Codex, Gemini, and Pi.
- gh-aw defaults to read-only, sandboxed agent jobs and routes configured writes through safe-output jobs; ferry's autonomous changes and merges depend on workflow configuration, branch protection, and CI gates.
- Both projects use the MIT license and are not archived; the supplied figures list 3 stars for ferry and 5.3k for gh-aw.
Choose ferry if you…
- want Jira ticket transitions to initiate an agent-led implementation pipeline.
- need a workflow with distinct refinement, development, review, iteration, and merge phases.
- want to run ticket work locally using isolated worktrees, or are evaluating experimental GitLab CI support.
Choose gh-aw if you…
- want to define AI-assisted repository tasks in Markdown and compile them into GitHub Actions workflows.
- need agent help interpreting issues, pull requests, CI results, or project documentation within existing GitHub Actions.
- want read-only, sandboxed agent jobs by default, with configured writes handled through safe outputs.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.