What it does
Cactus lets app makers run AI on the device itself, such as a phone or smart watch, instead of sending everything to the cloud. It handles chat, speech-to-text, image understanding and search over documents.
It shrinks models so they fit and run fast on small chips. Its makers say it can hand difficult questions to a cloud model automatically when the local model is unsure, and this can be turned off.
Developers can use it from C, Python, Flutter and React Native, and there is a quick demo for Mac.
Who it's for
Mobile and device developers who want AI to run on the device.
Can I use it without coding?
Developers only. Mainly a toolkit for app developers, though a Mac demo runs with two commands. New to this? Start here.
Can I run it?
- Runs on
- Mac, Linux, Phone
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe
Where people are talking about it
- Launch HN: Cactus (YC S25) – AI inference on smartphonesHacker News · Sept 2025
- Show HN: Cactus – Ollama for SmartphonesHacker News · Jul 2025