TrendRadar is an AI-driven public opinion and trend monitoring system built in Python that aggregates trending topics from multiple platforms and filters them through intelligent analysis. The project aims to combat information overload by providing users with curated news and trending content relevant to their interests. It combines multi-platform data aggregation, RSS subscription capabilities, and AI-powered filtering to deliver personalized trend insights directly to users' devices.
The core functionality centers on aggregating hot topics and news from various platforms, then applying AI-based filtering to identify content matching user-specified keywords and interests. The system supports AI-powered translation of news content and generates AI-driven analytical summaries that can be pushed directly to mobile devices and other endpoints. The project integrates with the Model Context Protocol architecture, enabling natural language dialogue analysis, sentiment analysis, and trend prediction capabilities through AI interfaces. Users can deploy TrendRadar via Docker or locally, with data storage options for both local and cloud-based solutions.
The notification and delivery system is comprehensive, supporting integration with WeChat, Feishu, DingTalk, Telegram, email, ntfy, Bark, and Slack channels for intelligent message distribution. Recent updates in version 6.10.0 introduced batch processing for AI translations to handle large volumes of content without exceeding request limits, along with modular restructuring that separated the AI filtering pipeline into independent components for improved maintainability. The mcp-v4.0.0 release added the ability to push AI-generated messages across all supported channels with automatic Markdown formatting adaptation and intelligent message batching based on each platform's character or byte limits.
The project emphasizes lightweight deployment and ease of use, with documentation highlighting a 30-second deployment capability. The official website at trendradar.sandev.cc provides comprehensive documentation and quick-start guides. The repository acknowledges its dependency on the newsnow project for multi-platform data acquisition and maintains active community engagement through GitHub issues, a WeChat public account, and a QQ group for user support and feedback. The project accepts financial support through WeChat and Alipay channels to sustain ongoing development and API costs.
