actions/ai-inference

An action for calling AI models with GitHub Models

What it solves

This project provides a GitHub Action that allows developers to integrate AI-powered inference directly into their CI/CD workflows. It eliminates the need to write custom scripts to call AI models, providing a standardized way to run prompts against the GitHub Copilot CLI.

How it works

The action acts as a wrapper around the GitHub Copilot CLI. It takes a prompt (provided inline or via a file) and a system prompt, sends them to the Copilot CLI, and returns the model's response as a workflow output or a temporary file.

Who it’s for

Developers and DevOps engineers who use GitHub Copilot and want to automate AI tasks—such as summarizing repository changes or analyzing code—within their GitHub Actions workflows.

Highlights

  • Flexible Prompting: Supports inline prompts, plain text files, and structured .prompt.yml files with template variables.
  • Variable Injection: Allows injecting content from other files into prompts using the file_input parameter.
  • Model Selection: Enables specifying the model to be used (e.g., gpt-4.1, claude-sonnet-4.5).
  • Model Response Handling: Outputs the response as both a string and a path to a temporary file for easier processing in subsequent workflow steps.

Related

  • Project
    github/app

    The GitHub Copilot app is a desktop client that lets you run Copilot‑powered AI agents in isolated local or cloud workspaces, manage multiple parallel sessions, and oversee the entire coding workflow—from picking a task to merging a PR—through visual canvases and automation tools.

  • Project
    google-github-actions/run-gemini-cli

    A GitHub Action that integrates Gemini AI into development workflows to automate PR reviews, issue triage, and provide conversational AI assistance directly in GitHub.

  • Project
    github/gh-aw

    GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension that lets you write AI‑powered automation as Markdown files with YAML front‑matter. The tool compiles these *agentic* workflows into standard GitHub Actions workflows, running LLMs (Copilot, Claude, OpenAI, Gemini, Pi) in a sandboxed, read‑only mode. Writes are gated through a separate safe‑outputs job with scoped permissions. It’s designed for tasks like issue triage, PR review, CI failure analysis, docs updates, and repo reporting, integrating securely with existing CI/CD pipelines.

  • Project
    github/accessibility-scanner

    A GitHub Action that scans websites for accessibility barriers and uses GitHub Copilot to automatically propose AI-powered fixes through GitHub issues.

  • Project
    anthropics/claude-code-base-action

    A GitHub Action that integrates Claude Code into CI/CD workflows, enabling automated agentic coding tasks like PR reviews and dependency updates.