Home› Projects› nativ
nativ
Swift

nativ

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

by Neywa-Labs · GitHub
Stars
Forks
License
Created
Last commit
Language
Likely
Self-hostable
apple-siliconllmlocal-aiMITSwiftSelf-hostable
View on GitHub
In plain words

Run AI models directly on your Mac without sending data online, keeping everything local.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
nativ — GitHub preview card
📈 Star history
1.59k1.57k
2026-11-042026-11-15
📈 Track nativ

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

nativ has 1.6k stars on GitHub. It has been forked 114 times. nativ is written mainly in Swift. It has been in active development since 2026. nativ is available under the MIT license. Its main topics are apple-silicon, llm, local-ai, macos.

❓ Frequently asked questions

What is nativ?

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

Is nativ open source?

nativ is an open-source project. It is released under the MIT license.

Is nativ free?

Yes. nativ is free and open source — you can use, modify and self-host it.

What license does nativ use?

nativ is available under the MIT license.

What language is nativ written in?

nativ is written mainly in Swift.

🏅 Maintainer of this project?
olud.ai badge — nativ

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=neywa-labs-nativ)](https://olud.ai/project/neywa-labs-nativ.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.