Skip to content

Commit 6294bcf

Browse files
committed
chore: update README & doc
1 parent d07f009 commit 6294bcf

File tree

3 files changed

+49
-42
lines changed

3 files changed

+49
-42
lines changed

README.md

Lines changed: 49 additions & 42 deletions
Original file line numberDiff line numberDiff line change
@@ -1,22 +1,57 @@
1+
<p align="center">
2+
<a href="https://minitap.ai">
3+
<img src="./doc/readme-banner.gif" alt="Project banner" />
4+
</a>
5+
</p>
6+
7+
<div align="center">
8+
9+
[![GitHub stars](https://img.shields.io/github/stars/minitap-ai/mobile-use?style=for-the-badge&color=e0a8dd)](https://github.com/minitap-ai/mobile-use/stargazers)
10+
[![Discord](https://img.shields.io/discord/1403058278342201394?color=7289DA&label=Discord&logo=discord&logoColor=white&style=for-the-badge)](https://discord.gg/ZZbKEZZkwK)
11+
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge)](https://opensource.org/license/mit)
12+
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=for-the-badge)](CONTRIBUTING.md)
13+
14+
[minitap.ai](https://minitap.ai)
15+
16+
</div>
17+
118
# mobile-use: automate your phone with natural language
219

20+
Mobile-use is a powerful, open-source AI agent that controls your Android or IOS device using natural language. It understands your commands and interacts with the UI to perform tasks, from sending messages to navigating complex apps.
21+
22+
![mobile-use in Action](./doc/linkedin-demo.gif)
23+
24+
## ✨ Features
25+
26+
- **Natural Language Control**: Interact with your phone using your native language.
27+
- **UI-Aware Automation**: Intelligently navigates through app interfaces.
28+
- **Data Scraping**: Extract information from any app and structure it into your desired format (e.g., JSON) using a natural language description.
29+
- **Extensible & Customizable**: Easily configure different LLMs to power the agents that power mobile-use.
30+
31+
## Benchmarks
32+
333
<p align="center">
4-
<img src="./doc/readme-banner.gif" alt="readme-banner" width="800"/>
34+
<img src="./doc/benchmark.png" alt="Project banner" />
535
</p>
636

7-
### TL;DR
37+
We are global number 1 Opensource pass@1 on the AndroidWorld benchmark.
838

9-
**What is it?** An AI agent to control your phone (IOS/Android) with natural language.
39+
More info here: https://minitap.ai/research/mobile-ai-agents-benchmark
40+
41+
## 🚀 Getting Started
42+
43+
Ready to automate your mobile experience? Follow these steps to get mobile-use up and running.
44+
45+
### Quick Launch (Docker)
1046

11-
> **Note:** This quickstart, with everything dockerized, is only available for Android devices/emulators as of now.
47+
> [!NOTE]
48+
> This quickstart, is only available for Android devices/emulators as of now, and you must have Docker installed.
1249
13-
**How to run?**
50+
First:
1451

1552
- Either plug your Android device and enable USB-debugging via the Developer Options
1653
- Or launch an Android emulator
1754

18-
> **Note:** You must have Docker installed for this quickstart to work.
19-
2055
Then run in your terminal:
2156

2257
1. For Linux/macOS:
@@ -37,40 +72,10 @@ powershell.exe -ExecutionPolicy Bypass -File minitap.ps1 `
3772
--output-description "A JSON list of objects, each with 'sender' and 'subject' keys"
3873
```
3974

40-
> **Note:** If using your own device, make sure to accept the ADB-related connection requests that will pop up on your device.
75+
> [!NOTE]
76+
> If using your own device, make sure to accept the ADB-related connection requests that will pop up on your device.
4177
> Similarly, Maestro will need to install its APK on your device, which will also require you to accept the installation request.
4278
43-
<div align="center">
44-
45-
[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
46-
[![Python Version](https://img.shields.io/badge/python-3.12-blue.svg)](https://www.python.org/downloads/release/python-3120/)
47-
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
48-
49-
</div>
50-
51-
---
52-
53-
## 💡 What is mobile-use?
54-
55-
Mobile-use is a powerful, open-source AI agent that controls your Android or IOS device using natural language. It understands your commands and interacts with the UI to perform tasks, from sending messages to navigating complex apps.
56-
57-
![mobile-use in Action](./doc/linkedin-demo.gif)
58-
59-
## ✨ Features
60-
61-
- **Natural Language Control**: Interact with your phone using your native language.
62-
- **UI-Aware Automation**: Intelligently navigates through app interfaces.
63-
- **Data Scraping**: Extract information from any app and structure it into your desired format (e.g., JSON) using a natural language description.
64-
- **Extensible & Customizable**: Easily configure different LLMs to power the agents that power mobile-use.
65-
66-
## 🚀 Getting Started
67-
68-
Ready to automate your mobile experience? Follow these steps to get mobile-use up and running.
69-
70-
### Quick Launch (Docker)
71-
72-
For the fastest way to get started, please see the [TL;DR](#tldr) section at the top of this document for a one-command Docker setup.
73-
7479
### Manual Launch (Development Mode)
7580

7681
For developers who want to set up the environment manually:
@@ -83,7 +88,8 @@ Mobile-use currently supports the following devices:
8388
- **Android Simulators**: Set up through Android Studio.
8489
- **iOS Simulators**: Supported for macOS users.
8590

86-
> **Note**: Physical iOS devices are not yet supported.
91+
> [!NOTE]
92+
> Physical iOS devices are not yet supported.
8793
8894
#### 2. Prerequisites
8995

@@ -163,12 +169,13 @@ python ./src/minitap/main.py \
163169
--output-description "A JSON list of objects, each with 'sender' and 'subject' keys"
164170
```
165171

166-
> 💡 **Note:** If you haven't configured a specific model, mobile-use will prompt you to choose one from the available options.
172+
> [!NOTE]
173+
> If you haven't configured a specific model, mobile-use will prompt you to choose one from the available options.
167174
168175
## ❤️ Contributing
169176
170177
We love contributions! Whether you're fixing a bug, adding a feature, or improving documentation, your help is welcome. Please read our **[Contributing Guidelines](CONTRIBUTING.md)** to get started.
171178

172179
## 📜 License
173180

174-
This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
181+
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

doc/benchmark.png

556 KB
Loading

doc/readme-banner.gif

4 MB
Loading

0 commit comments

Comments
 (0)