What it does
Needle is a tiny AI model, only a few megabytes, built to run on phones, wearables, robots, cars and other small devices. Instead of chatting, it focuses on turning what a person says into actions: it picks which of an app's functions to use and fills in the details.
It can also pull structured details out of messy text, such as an invoice or a booking, and turn sentences into numbers that help an app search and match things on the device. A companion speech-to-text model called Whistle lets it take voice input.
Its makers say it beats much larger models at these narrow tasks. Developers can fine-tune it on their own app's functions, either on their own computer or through the makers' paid platform.
Who it's for
App and device makers who want voice or text commands to work directly on small devices, without a big cloud model.
Can I use it without coding?
Developers only. It is a model and code library that developers build into their own apps; there is also a browser demo. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Phone, Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- 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.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Show HN: Needle: We Distilled Gemini Tool Calling into a 26M ModelHacker News · May 2026