gh-aw vs run-gemini-cli
AI-assisted automation in GitHub Actions compared
gh-aw defines AI-powered repository workflows in Markdown and compiles them into GitHub Actions. run-gemini-cli runs Gemini CLI within GitHub Actions; it focuses on Gemini-based coding tasks and on-demand help in issues and pull requests.
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.
run-gemini-cli: Run Gemini CLI in GitHub Actions
run-gemini-cli brings Gemini CLI into GitHub Actions for automated coding tasks and on-demand help in issues and pull requests. It suits teams that want AI-assisted reviews, triage, or repository changes within their existing workflows.
| gh-aw | run-gemini-cli | |
|---|---|---|
| Language | Go | TypeScript |
| License | MIT | Apache-2.0 |
| Stars | 5.4k | 2.1k |
| Forks | 596 | 288 |
| Last analyzed | Oct 23, 2026 | Oct 3, 2026 |
Key differences
- gh-aw supports several AI engines, including Copilot, Claude Code, Codex, Gemini, and Pi; run-gemini-cli is built around Gemini CLI.
- gh-aw compiles Markdown workflow definitions with YAML frontmatter into generated GitHub Actions files; run-gemini-cli is a GitHub Action configured through inputs and workflow examples.
- gh-aw defaults agent jobs to read-only access and sandboxing, with configured writes handled through safe-output jobs; run-gemini-cli relies on workflow permissions that users should scope carefully.
- gh-aw is written in Go and licensed under MIT; run-gemini-cli is written in TypeScript and licensed under Apache-2.0.
- gh-aw is suited to teams adding agent reasoning to varied repository tasks; run-gemini-cli suits teams seeking Gemini CLI coding work, reviews, triage, or comment-triggered assistance.
- Both are active projects for GitHub Actions, with gh-aw reporting 5.3k stars and 572 forks, and run-gemini-cli reporting 2.1k stars and 288 forks.
Choose gh-aw if you…
- need to define AI workflows in Markdown and compile them into GitHub Actions.
- want a choice of supported AI engines rather than a Gemini CLI-specific action.
- need read-only and sandboxed agent-job defaults with configured writes handled separately.
Choose run-gemini-cli if you…
- want to run Gemini CLI for repository events, scheduled tasks, or comment requests.
- need configurable Gemini authentication, including API key or Google Cloud options.
- want to configure prompts, models, CLI versions, settings, and extensions through action inputs.
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.