Hacker News new | ask | show | jobs
Show HN: SuprLogs – Autopilot changelogs from GitHub commits (suprlogs.com)
1 points by Aslanas 79 days ago
I hate writing changelogs. So usually, I don't. When I have, they've gotten stale or were way too technical for my audience.

At the same time I recognize they are critical for illustrating momentum to customers, investors, and colleagues.

So I built a tool to make it effortless, automatic, and something I'd never have to think about again.

My solution is simple: 1. Connect a repo 2. Done

SuprLogs reads every commit diff, generates analysis, writes unified changelog entries from that analysis, publishes, updates, etc. all on autopilot. It's basically a set-it-and-forget it system.

A few really cool features that I haven't seen anywhere else include: - Ability to connect multiple repos to create a single unified changelog - Ability to ingest every historic commit and backfill a changelog to the present day - Ability to set a custom system prompt to guide the writing style - Kanban style theme, similar to how PostHog does their changelog

I'd especially love feedback on: - Is the tool is useful with it's current features? What's it missing? - Do you like the themes? - Do you trust it with private repos? - Do you understand the value prop from the homepage?

Anyone can use it. It's free forever for public repos. And there's a no-credit-card free trial with all the bells and whistles if you want to give it a deeper dive (private repos, analytics, teams, etc).

Happy to answer any questions about the tech, orchestration, durability, security, etc.

1 comments

interesting, a question will it download the code ? how does it work technically ?
When you connect a Github repository it uses the Github API to download all the diff changes from each commit. Then it uses an LLM to analyze each commit's material changes (ignoring lock files, compiled directories, vendor dependencies, etc.) to write a markdown diff-summary before discarding the commit data (as part of my zero retention policy).

Finally, it uses those diff-summary markdowns to write a changelog entry for each relevant period (e.g. daily, weekly, or monthly changelog summaries).

The pipeline uses Inngest for durability to fetch the diffs, write the summaries, and write the changelog entries. I use Inngest to manage all the pipelines so things keep processing smoothly regardless of Github or LLM API rate limits.

You can brink your own LLM keys for unlimited commits (and more privacy) or use the one I provide with limits on each plan.

Here's an example of the final output https://changelog.suprlogs.app/