CatDoes v3
Team of AI agents build mobile apps for you & your business
In plain words
CatDoes v3 is an AI platform that uses multiple agents to build mobile and web applications for users and businesses without requiring coding knowledge. The tool enables anyone to create apps and publish them to the App Store, regardless of technical experience. Version 3 introduces web deployment capabilities, GitHub integration for syncing projects to remote repositories, daily credits for users, and improved user interface and experience design.
written from the facts on this page · September 2026
From the sources
CatDoes uses a multi-agent approach to build mobile apps for you and your business using AI. It's so easy to use that anyone, regardless of their technical experience, can build a mobile app and publish it on the App Store using CatDoes. In v3 we've added web deployments so you could deploy your project as a web app. We've also added a first-class GitHub integration which allows you to sync your project with a remote repo, tons of UI/UX improvements, daily credits for all, and much more!
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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology