Kane CLI
Natural language browser & mobile app tests from terminal
In plain words
Kane CLI is a command-line tool that runs browser and mobile app tests written in natural language. Developers and AI coding agents describe what they want to test, and the tool executes it in a real Chrome browser, returning pass or fail results with shareable proof. It requires no selector writing and operates locally, making it free to start. The tool integrates with existing development workflows and can read project documentation to automatically generate test scenarios.
written from the facts on this page · September 2026
From the sources
An agentic quality verifier for developers and AI coding agents. Describe a test in natural language, and Kane CLI runs it in a real Chrome browser and returns pass or fail with shareable proof. No selectors to write. Local-first, free to start.
Kane CLI is a command-line tool for AI browser automation. Describe a test in natural language; it drives real Chrome from your terminal and returns pass or fail.
End-to-end flows on your local browser, powered by natural language. Instant validation, deep bug discovery, and production-ready automation that elevates release confidence. Point Cursor to Kane CLI and let it drive real browsers. Author, run, and verify flows straight from your editor. One unbroken run, in the terminal you already use — kane drives a requirement from context to proof and keeps it there. Watch the whole session type itself out, line by line. kane reads your PRDs, tickets, and existing suites, then draws the graph of everything your product promises — sources, use-cases, scenarios, and acceptance criteria — before a single test runs. A criterion only counts once a test ran…from testmuai.com
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 · 16d 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, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com