Install
openclaw skills install hinge-likerAutomated Hinge dating profile liker using Android emulator + Gemini vision AI. Scrolls through full profiles, analyzes attractiveness with AI, likes the bes...
openclaw skills install hinge-likerAutomates Hinge swiping on an Android emulator. Uses Gemini vision to evaluate profiles, pick the best photo/prompt, and send witty comments.
adb in PATHGEMINI_API_KEY environment variable (Gemini 2.5 Flash recommended)brew install --cask android-commandlinetools)avdmanager create avd -n HingePhone -k "system-images;android-34;google_apis;arm64-v8a" -d pixel_6GEMINI_API_KEY in environment# Set environment
export PATH="<android-tools-path>/platform-tools:<android-tools-path>/emulator:$PATH"
export GEMINI_API_KEY="your-key-here"
# Boot emulator (windowed for video, add -no-window for headless)
emulator -avd HingePhone -no-audio -no-metrics -gpu swiftshader_indirect &
# Wait for boot
adb wait-for-device
while [ "$(adb shell getprop sys.boot_completed 2>/dev/null | tr -d '\r')" != "1" ]; do sleep 2; done
# Launch Hinge
adb shell am start -a android.intent.action.MAIN -n co.hinge.app/.ui.AppActivity
sleep 10
# Optional: start screen recording
adb shell screenrecord --time-limit 300 /sdcard/hinge_session.mp4 &
# Run the liker
python3 scripts/hinge_android.py --likes 8 --user-desc "a 25yo tech guy in SF who's fit and active"
# Pull recording + kill emulator
adb shell pkill -INT screenrecord; sleep 3
adb pull /sdcard/hinge_session.mp4 ./recordings/session.mp4
adb emu kill
| Flag | Default | Description |
|---|---|---|
--likes | 8 | Max likes per session |
--adb | adb | Path to adb binary |
--user-desc | generic | Description of the user for AI matching |
| Variable | Required | Description |
|---|---|---|
GEMINI_API_KEY | Yes | Google Gemini API key |
GEMINI_MODEL | No | Model name (default: gemini-2.5-flash) |
ADB_PATH | No | Full path to adb binary |
HINGE_WORK_DIR | No | Working directory for screenshots/logs |
The script prints a session report to stdout with:
JSON logs are saved to logs/ directory.
Set up via OpenClaw cron for daily automated runs. Key notes:
am start to launch Hinge, not monkey (more reliable)ffmpeg -i input.mp4 -vcodec libx264 -crf 28 -preset fast -vf scale=720:-2 output.mp4Send the user a text report including:
maxOutputTokens, check API key/quota.find_all_hearts() and find_skip_button() patterns.df -h), try -gpu swiftshader_indirect.