Repolode
Submit
sansan0

sansan0/TrendRadar

Self-hosted hot-news monitor that aggregates trending topics from Chinese platforms and RSS feeds, filters by keyword or AI, and pushes digests to chat and email channels.

View on GitHubWebsite
Stars
63,044
Forks
24,910
Open issues
32
Last commit
5 days ago

What is it?

TrendRadar collects trending topics from around a dozen Chinese news and social platforms, along with RSS and Atom feeds, then groups matching items by user-defined keywords. It tracks how each story's rank changes over time, marks newly appearing topics, and produces an HTML report that can also be published as a static page.

Filtering can be done with keyword files, including regex patterns, or with AI, where interests are written in plain language and the model scores each headline. Optional AI features cover analysis summaries, translation into other languages, and an MCP server for querying the collected data through conversational AI clients.

Delivery supports WeChat Work, personal WeChat, Feishu, DingTalk, Telegram, email, ntfy, Bark, Slack and generic webhooks. The project can run on GitHub Actions, in Docker, or locally with uv, and stores data in local SQLite or S3-compatible cloud storage.

Key features

  • 01Aggregates hot lists from about 11 Chinese platforms, plus custom RSS and Atom feeds.
  • 02Filters content by keyword files with regex support or by AI-scored natural-language interests.
  • 03Marks newly appearing topics and tracks rank changes across collection runs.
  • 04Pushes reports to WeChat Work, Feishu, DingTalk, Telegram, email, ntfy, Bark, Slack and webhooks.
  • 05Provides an MCP server so AI clients can query collected news data.
  • 06Runs via Docker, GitHub Actions or locally, with SQLite or S3-compatible storage.

Use cases

  • Monitoring public opinion or brand mentions across Chinese news and social platforms.
  • Following industry or investment news and receiving only new items by chat or email.
  • Building a daily digest of trending topics on a home server or NAS.
  • Letting an AI assistant query recent trending news through MCP.

Quick start

  1. 1

    Open the Quick Start section of the README (快速开始) and pick Docker or local deployment

  2. 2

    Follow the Docker deployment guide in the README (Docker 部署 section)

Things to know

  • Licensed under GPL-3.0, a copyleft license that requires derivative works to remain open source.
  • Hot-news data comes from the newsnow API run by a third party, and the README asks Docker users to keep push frequency reasonable.

Topics

#news-aggregation#hot-news#rss#llm#docker#self-hosted#notifications#data-analysis#ai#bark

FAQ

What is TrendRadar?
Self-hosted hot-news monitor that aggregates trending topics from Chinese platforms and RSS feeds, filters by keyword or AI, and pushes digests to chat and email channels. TrendRadar collects trending topics from around a dozen Chinese news and social platforms, along with RSS and Atom feeds, then groups matching items by user-defined keywords. It tracks how each story's rank changes over time, marks newly appearing topics, and produces an HTML report that can also be published as a static page.
Is TrendRadar free to use? What license does it have?
TrendRadar is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
Is TrendRadar still maintained?
Actively maintained. The last commit to TrendRadar was on Oct 15, 2026.
What can I use TrendRadar for?
Monitoring public opinion or brand mentions across Chinese news and social platforms. Following industry or investment news and receiving only new items by chat or email. Building a daily digest of trending topics on a home server or NAS. Letting an AI assistant query recent trending news through MCP.
How do I install TrendRadar?
Open the Quick Start section of the README (快速开始) and pick Docker or local deployment Follow the Docker deployment guide in the README (Docker 部署 section)
Where can I get TrendRadar?
The source code and installation instructions are on GitHub: https://github.com/sansan0/TrendRadar

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects