Credentials. Accessibility access lets the Agent read visible chat text, and screenshots are sent to your configured model provider, so only use it with a provider and app you trust.
Who it is forAn Android user who gets many chat messages and wants a suggested reply copied to the clipboard for review.
The problemComposing replies in busy chat apps takes effort, and manually copying context into an AI app is slow.
The outcomeA suggested reply is copied to the clipboard for you to review and paste yourself.
What you need first
- Windows x86-64 PC with Python 3.13 for the provided build script
- Internet access for the first build to download Briefcase, the Android SDK, Gradle, and Maven dependencies
- Android 11+ arm64 device or emulator
- An OpenAI-compatible HTTPS provider base URL, model ID, and API key
Steps
- Open Settings > Phone Control and enable the Muse Lite accessibility service in Android system settings.
- Grant notification permission when Android asks, then turn on Allow Agent to operate the phone.
- Configure a vision-capable model in Settings and turn on image input if you want screenshot help.
- Enter “读取我正在聊天的界面,推荐一个回复并复制到剪贴板” in the conversation input, then switch to the chat app within the 30 second wait.
- Paste the copied reply yourself after reviewing it; the Agent does not send messages or paste text.
Prompt for your agent
In the yxq953/MuseLite app with Phone Control enabled, ask the Agent to read the visible chat in <app name> and copy one suggested reply to the clipboard. Expected output: a short reply reported by the Agent and a clipboard write result. Verify that the clipboard now holds the reply and that no message was sent in the chat app.
Caveat. Phone control only reads visible screen text, so hidden history or apps that do not expose text may need a screenshot with an image-capable model.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page