Generate professional changelogs from Git commits with GPT-4 and GitHub

AI-Powered Git Changelog Generator for Automated Release Notes

This workflow transforms your software release process by automatically generating clean, professional changelogs from your Git commit history. It listens for new version tags in your GitHub repository, uses AI to summarize the changes, and publishes a polished release note, saving you hours of manual work.

Disclaimer This template is designed for self-hosted n8n instances and requires API credentials for GitHub and an AI provider (e.g., OpenAI, Google Gemini).

🚀 Key Features Fully Automated Process: Triggers automatically on a git push --tags event. Set it up once and forget about it. AI-Powered Summarization: Leverages a Large Language Model (LLM) to intelligently read, categorize, and summarize your commit messages into a human-friendly format. Seamless GitHub Integration: Fetches commit data and creates official GitHub Releases without leaving the n8n environment. Smart Categorization: Automatically groups release notes into sections like "Features," "Fixes," and "Other Changes" for clarity. Highly Customizable: Easily adapt the AI prompt, changelog format, and release template to match your project's style. Saves Developer Time: Eliminates the tedious, manual task of writing release notes, freeing up developers to focus on coding.

⚙️ How It Works The workflow is a linear process triggered by a webhook from GitHub.

1. GitHub Webhook Trigger A Webhook node is configured to listen for push events from your specified GitHub repository. It is filtered to only run when a new tag (e.g., v1.2.0) is pushed, which is the standard practice for signaling a new release.

2. Fetch Commit History Once triggered, a GitHub node uses the webhook payload to identify the repository and the new tag. It makes an API call to GitHub to compare the new tag with the most recent previous tag, fetching all the commit messages in between.

3. AI Summarization The list of raw commit messages is passed to an AI node (e.g., OpenAI or Google Gemini). A pre-defined prompt instructs the AI to process the commits. The prompt asks the model to summarize the changes and group them into logical categories. The AI returns a single, well-formatted markdown text block representing the complete changelog.