Open-source LLM-powered test automation library for mobile and web
Hey HN! I'm Alex, a tech lead of the Selenium project and a QA engineer. For the last 10 months, I've been working on Alumnium - a test automation library that should make my life easier and let me write less code when automating the tests. The goal is to use LLM for _automating_ so I could focus more on _testing_. Unlike other similar projects, Alumnium can be used in existing tests without changes to test runners, reporting tools, or any other test infrastructure. This allows me to gradually migrate my test suites (mostly Selenium) and revert whenever something goes wrong (this happens a…
In plain words
Alumnium is an open-source test automation library that uses large language models to reduce code needed for writing mobile and web tests. Built for QA engineers and developers, it integrates with existing test suites without requiring changes to test runners or infrastructure, allowing gradual adoption. It supports both Appium and Playwright, uses low-cost models like GPT-4o Mini, and includes built-in caching for performance. Unlike AI agents, it fails tests rather than working around issues, helping teams focus on testing strategy over automation implementation.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! I'm Alex, a tech lead of the Selenium project and a QA engineer. For the last 10 months, I've been working on Alumnium - a test automation library that should make my life easier and let me write less code when automating the tests. The goal is to use LLM for _automating_ so I could focus more on _testing_. Unlike other similar projects, Alumnium can be used in existing tests without changes to test runners, reporting tools, or any other test infrastructure. This allows me to gradually migrate my test suites (mostly Selenium) and revert whenever something goes wrong (this happens a lot, to be honest). Other major differences: - cheap (works on low-tier models like gpt-4o-mini, costs $20 per month for 1k+ tests) - not an AI agent (dumb enough to fail the test rather than working around to make it pass) - fast thanks to a built-in caching - supports both mobile (Appium) and web (Playwright, Selenium) - supports completely local execution (Ollama) The project is still in a very much experimental phase, but I'd be happy to get any feedback.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
