SuYxh/ai-news-aggregator

🤖 AI News Aggregator - 自动聚合 80+ AI/科技资讯源，支持 RSS 订阅导入，智能过滤 AI 相关内容，双语标题翻译，每 2 小时自动更新

What it solves

Keeping up with the fast-moving AI field is hard when news is scattered across dozens of websites, WeChat accounts, and RSS feeds. This project pulls everything into one place, filters for AI-relevant content, and updates automatically every two hours. It also translates English titles into Chinese so non-English readers can quickly scan what matters.

How it works

The project runs a TypeScript-based scraper that pulls from 14 aggregator platforms (like AI Today Hot List, TechURLs, NewsNow, TopHub, and more), 70+ carefully selected RSS feeds (including official AI company accounts, Chinese AI firms, researchers, tools, and blogs), and 52 WeChat public accounts. It uses keyword matching to decide if an item is AI-related, deduplicates results, and stores everything as JSON files. A React + TypeScript web app (built with Vite and Tailwind CSS) reads those JSON files and presents the news with filtering, search, dark mode, favorites, reading history, and time-range options. The GitHub Actions workflow re-runs the fetch and deploy process every two hours, so the hosted site stays fresh.

Who it’s for

AI enthusiasts, developers, researchers, and tech-curious readers who want a single, current, and bilingual stream of AI news. It’s also useful for anyone who wants structured JSON data for their own analysis or integrations.

Highlights

  • Aggregates from 14 professional platforms, 70+ RSS feeds, and 52 WeChat official accounts
  • Automatic English-to-Chinese title translation with three display modes (original, Chinese, bilingual)
  • Web app with responsive design, dark mode, search, filters, favorites, reading history, and JSON export
  • Scheduled GitHub Actions workflow updates news every 2 hours
  • Clean JSON output in data/ with files for 24h, 7d, archive, source status, and more
  • Fully customizable: edit the OPML file to add RSS feeds, adjust fetch time windows, and choose output directories

Related

  • Project
    Project-AgML/AgML

    AgML is a Python library that provides easy access to a curated collection of public agricultural image datasets via the Hugging Face Hub. It offers unified loaders, lazy loading for huge image‑text datasets, and standard annotation schemas, enabling seamless use with the `datasets` and `transformers` ecosystems for training TensorFlow or PyTorch models.

  • Project
    qdrant/go-client

    A Go client library for the Qdrant vector search engine, providing utilities to manage collections and perform similarity searches.

  • Project
    kamu-data/kamu-cli

    kamu is a command-line tool for managing and processing dynamic structured data with a tamper-proof ledger and verifiable transformations. It enables building ETL pipelines that can be shared and verified across organizations, much like Git for data.

  • Project
    MinishLab/vicinity

    Vicinity is a lightweight Python library that provides a unified, low‑dependency interface for nearest‑neighbour search over vector embeddings. It supports many back‑ends (FAISS, HNSW, Annoy, etc.), offers easy serialization (local disk or Hugging Face Hub), and includes a simple evaluation tool for measuring speed and recall.