This Python application, called lifelog.ai, is designed to capture screenshots at regular intervals, process them, and interact with various AI models for analysis. The application provides a user interface for configuration and control.
-
Clone the repository
-
Install the required dependencies:
pip install -r requirements.txtRun the app.py script to start the application:
python app.pyor create executable with:
pyinstaller --onefile --windowed app.pyOnce the application starts, you'll see a graphical user interface (GUI) where you can configure the interval between screenshots, select the desired quality, choose the AI model for analysis, and start or stop the screenshot process.
-
Automatic Screenshot Capture: lifelog.ai captures screenshots at regular intervals from all connected monitors.
-
Quality Adjustment: The application allows you to adjust the quality of the captured screenshots to optimize file size and clarity.
-
AI Model Integration: lifelog.ai integrates with two AI models for image analysis: GPT (OpenAI) and Moondream. These models can analyze the captured screenshots and provide insights based on the selected model.
-
Database Storage: Captured screenshots and corresponding AI analysis results are stored in a SQLite database (
data/*.db) for future reference.
-
Interval: Set the time interval (in minutes) between consecutive screenshots.
-
System Prompt: Customize the default prompt used when interacting with the AI models.
-
Quality: Choose the desired quality percentage for the captured screenshots.
-
Model Selection: Select the AI models (GPT/Together/Whisper/Moondream) for image/audio analysis.
- Python 3.x
base64sqlite3tempfilerequestspyautoguitkinterPILgradio_clientdotenvscreeninfo
Contributions are welcome! If you have any suggestions, enhancements, or bug fixes, feel free to open an issue or create a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.