sansan0/TrendRadar

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

What it solves

TrendRadar is a lightweight, easy-to-deploy news and trend monitoring assistant. It solves the problem of "information overload" by filtering out noise and delivering only the news and updates that the user actually cares about from multiple platforms and RSS feeds.

How it works

The system collects data from various trending lists and RSS/Atom feeds. It then processes this information using two primary methods: keyword-based filtering (including support for regular expressions) and AI-driven intelligent screening. The processed content is then delivered via a wide range of of notification channels (such as Telegram, Slack, Feishu, DingTalk, and Email) or rendered into an interactive HTML report.

Who it’s for

It is designed for users who want to stay updated on specific topics without manually browsing multiple sites, as well as developers and researchers who need to track industry trends and sentiment analysis in real-time.

Highlights

  • AI-Powered Insights: Uses LLMs (via LiteLLM) to provide deep trend analysis, sentiment detection, and automatic multi-language translation.
  • Intelligent Screening: Allows users to define interests in natural language (e.g., "I want to see AI and new energy news"), and AI automatically scores and filters the content.
  • MCP Server Support: Includes a Model Context Protocol (MCP) server that allows AI agents to search news, read full articles via Jina AI, and analyze trends.
  • Extensive Delivery: Supports 9+ notification channels and generates interactive HTML reports with dark mode and search functionality.
  • Flexible Scheduling: Features a unified scheduling system with presets (e.g., morning/evening summaries) to control when data is collected, analyzed, and pushed.