What do you want to do?
3 use cases
-
Run a local LLM inside a Python script with Uzu
Add Uzu with uv, download a small Qwen model and get a chat reply on your own machine.
View prompt
Add trymirai/uzu to this Python project with `uv add uzu==0.6.13` and write a script that downloads alibaba:qwen3.5:0.8b:mirai:mirai-m:4 and answers <question> locally, following the README Python quick start.
-
Add on-device AI chat to a Swift app with Uzu
Add the Uzu Swift package and run chat locally on Apple devices using unified memory.
- REPO
trymirai/uzu - Claude Code
- Cursor
- Software and DevOps
- Intermediate
View prompt
Add trymirai/uzu to my Swift app <app> and build a chat screen that downloads the Qwen 3.5 0.8B mirai model on first launch and replies on device, following the README Swift example.
- REPO
-
Stream local LLM replies in a Node or Rust app
Use Uzu's TypeScript or Rust API to stream chat replies and count generated tokens.
- REPO
trymirai/uzu - Claude Code
- Codex
- Cursor
- Software and DevOps
- Intermediate
View prompt
Using trymirai/uzu, write a <Rust or TypeScript> CLI that streams a local reply to <prompt> and prints generated tokens, based on the README chat example.
- REPO
Quick start with Uzu
- Check you have what it needs: Rust, Python (uv), Swift or TypeScript (pnpm); An Apple device to benefit from unified memory; Disk space for the downloaded model.
- Open trymirai/uzu on GitHub and read the README and license.
- Run
uv add uzu==0.6.13 - Create the engine with EngineConfig.create() and Engine.create as in the README Python example
- Load the model
alibaba:qwen3.5:0.8b:mirai:mirai-m:4and iterate the download to show progress - Open a chat session and send a system and a user ChatMessage
These steps come from our top use case, Run a local LLM inside a Python script with Uzu, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for trymirai/uzu
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forApp developers who want on-device LLM chat in a Mac, iOS, Python or Node app without paying per token.
- Why it is hot3k stars, talked about in 3 AI sources we track
- LanguageRust
- Sourcegithub.com/trymirai/uzu ยท Back to Hot repos
Requirements
- Rust, Python (uv), Swift or TypeScript (pnpm)
- An Apple device to benefit from unified memory
- Disk space for the downloaded model
Add this badge to your README
Maintain Uzu? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/trymirai-uzu/?utm_source=github&utm_medium=badge&utm_campaign=trymirai-uzu)
HTML
<a href="https://dedupedai.com/use-cases/trymirai-uzu/?utm_source=github&utm_medium=badge&utm_campaign=trymirai-uzu"><img src="https://dedupedai.com/badge/trymirai/uzu.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Uzu
What is Uzu?
uzu is a high-performance inference engine for running AI models directly inside your app, with zero latency, full data privacy and no inference costs. It has a simple high-level API in Rust, Python, Swift and TypeScript, downloads models such as Qwen 3.5 0.8B automatically, uses unified memory on Apple devices and supports streaming chat replies. It is an open-source project on GitHub: https://github.com/trymirai/uzu.
How do I use Uzu?
Run uv add uzu==0.6.13; then create the engine with EngineConfig.create() and Engine.create as in the README Python example; load the model alibaba:qwen3.5:0.8b:mirai:mirai-m:4 and iterate the download to show progress. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Uzu for?
App developers who want on-device LLM chat in a Mac, iOS, Python or Node app without paying per token.
What can I do with Uzu?
3 use cases so far, for example: Run a local LLM inside a Python script with Uzu; Add on-device AI chat to a Swift app with Uzu; Stream local LLM replies in a Node or Rust app. Each has steps and a copy-paste agent prompt.
What do I need to run Uzu?
Rust, Python (uv), Swift or TypeScript (pnpm); An Apple device to benefit from unified memory; Disk space for the downloaded model.
What are alternatives to Uzu?
Other hot AI repos in Software and DevOps: Skills, Claude Mem, Freellmapi, Andrej Karpathy Skills, Agent Desktop.
Is Uzu safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.