|
1
|
<h1 align="center"> |
|
2
|
<br> |
|
3
|
Onde |
|
4
|
<br> |
|
5
|
</h1> |
|
6
|
|
|
7
|
<p align="center"> |
|
8
|
<strong>On-device inference for cross-platform apps.</strong> |
|
9
|
<br> |
|
10
|
Run LLMs, diffusion models, and speech-to-text locally — no cloud, no latency, no data leaving the device. |
|
11
|
</p> |
|
12
|
|
|
13
|
<p align="center"> |
|
14
|
<a href="https://crates.io/crates/onde"><img src="https://img.shields.io/crates/v/onde.svg" alt="crates.io"></a> |
|
15
|
<a href="https://docs.rs/onde"><img src="https://docs.rs/onde/badge.svg" alt="docs.rs"></a> |
|
16
|
<a href="#license"><img src="https://img.shields.io/badge/license-MIT%2FApache--2.0-blue.svg" alt="License"></a> |
|
17
|
</p> |
|
18
|
|
|
19
|
--- |
|
20
|
|
|
21
|
**Onde** is a Rust crate that gives your app on-device AI in a single dependency. It wraps [mistral.rs](https://github.com/EricLBuehler/mistral.rs) for LLM and image generation, and [whisper.cpp](https://github.com/ggerganov/whisper.cpp) (via [transcribe-rs](https://github.com/cjpais/transcribe-rs)) for speech-to-text — with a unified API that handles model discovery, HuggingFace Hub downloads, cache management, and GPU acceleration across every platform. |
|
22
|
|
|
23
|
## License |
|
24
|
|
|
25
|
MIT License |
|
26
|
|
|
27
|
--- |
|
28
|
|
|
29
|
## Copyright |
|
30
|
|
|
31
|
<p align="center"> |
|
32
|
2026 <a href="https://ondeinference.com">Onde Inference</a> |
|
33
|
</p> |