Report card

Do AI agents pick GitHub Actions?

How often agents choose GitHub Actions when a developer needs ci/cd — measured across Claude, GPT, Gemini.

GitHub Actions

#1 of 6 ci cd
28%Pick Rate
95% CI 20%37%

When developers ask an AI agent for ci cd, GitHub Actions is picked 28% of the time — ranking #1 of 6 measured across Claude, GPT, Gemini.

Picked 28% Named, not picked 64% Never surfaced 8%

Top pick in the category. 🟢

Awareness

0 docs in FineWeb (10BT sample) · 1 URLs in Common Crawl

In the raw web crawl, but thin in the filtered corpus models actually train on — an awareness gap at the source.

AdoptionDid the pick convert to installs? Public Adoption = npm downloads of your packages. The proof half of the funnel.

41.6M installs / month ▼ 2% MoM

Installs are roughly flat month over month.

Get the full report

The per-model and per-surface breakdown for GitHub Actions — where it wins, where it loses, and to whom — plus an alert when the Pick Rate moves.

About GitHub Actions

GitHub Actions is a CI/CD and workflow automation platform built into GitHub.

GitHub Actions lets developers automate build, test, and deployment pipelines by defining workflows in YAML that run in response to repository events such as pushes, pull requests, or on a schedule. Workflows are composed of jobs and steps, where each step can run shell commands or reusable Actions contributed by the community or written in-house. It is aimed at developers and teams who want to automate software delivery without leaving GitHub.

Where to start

Start by creating a `.github/workflows` directory in your repository and adding a YAML workflow file that defines your triggers, jobs, and steps. To write a custom Action in JavaScript or TypeScript, use the `@actions/core` package to handle inputs, outputs, logging, and exit codes.

Install

Links and summary verified from public sources.

The rest of the CI/CD ranking

← Full CI/CD leaderboard · How this is measured