This project provides an automated workflow for collecting and compiling daily news on any specified topic using an LLM-powered agent framework. It's designed for users who need to stay updated on specific fields without manual searching and curation, delivering a structured markdown report.

How It Works

The system leverages the Agently AI application development framework to orchestrate AI agents. Users input a topic, and agents automatically generate an outline, search for relevant news using keywords (e.g., via duckduckgo-search), filter and select pertinent articles, and then summarize them. The process culminates in a markdown file containing curated news, complete with titles, summaries, and links.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Run the application: python app.py
• Requires Python and an LLM API key configured in SETTINGS.yaml.
• Official Agently framework documentation: https://github.com/Maplemx/Agently

Highlighted Details

• Generates news collections on user-defined topics.
• Outputs results in a markdown file format.
• Utilizes duckduckgo-search for news retrieval.
• Powered by the Agently AI application development framework.

Maintenance & Community

• Community support available via Discord and WeChat groups.
• Contact email: developer@agently.cn
• Issue reporting via GitHub Issues.

Licensing & Compatibility

• The specific license is not explicitly stated in the README.

Limitations & Caveats

• The project is presented as a showcase and may require configuration of LLM API keys and settings.
• The README does not specify the exact Python version requirements or any hardware constraints beyond standard Python execution.