Seanium/FeedMe

😋 AI-powered, Lightweight RSS Reader. Supports: GitHub Pages | Vercel | Alibaba Cloud ESA Pages | Docker

What it solves

FeedMe is a lightweight, AI-powered RSS reader that eliminates the need for forced logins, app downloads, and bloated interfaces. It transforms a collection of RSS feeds into a clean, responsive static page where users can quickly grasp the main points of articles through AI-generated summaries.

How it works

The project uses a build-time process to aggregate content from configured RSS sources. It integrates with Large Language Models (LLMs) via API to automatically generate summaries for each article. This process is automated via GitHub Actions or Docker Cron jobs, which periodically fetch new content, generate summaries, and rebuild the static site for deployment to platforms like GitHub Pages, Vercel, or Aliyun ESA.

Who it’s for

Users who want a personalized, self-hosted RSS feed aggregator that provides concise summaries of news and articles without the tracking or complexity of traditional RSS readers.

Highlights

  • AI-Powered Summarization: Automatically generates article summaries using a customizable LLM configuration.
  • AI Configuration: Full control over the LLM API key, base URL, model name, and summary prompt.
  • AI-Driven Workflow: Automated updates via GitHub Actions or Docker, ensuring content stays fresh without manual intervention.
  • Flexible Deployment: Supports zero-cost static hosting on GitHub Pages, Vercel, and Aliyun ESA, or private Docker deployment.
  • Modern UI: A responsive design with light and dark theme support.

Related

  • Project
    DevXDojo/MrRSS

    An AI-enhanced RSS reader that provides automatic translation, summarization, and recommendations to streamline information consumption.

  • Project
    versun/RSSBox

    An intelligent RSS management tool that uses AI for translation, full-text extraction, and smart filtering of feeds.

  • Project
    Colin-XKL/FeedCraft

    FeedCraft is an open‑source Go service that acts as middleware for RSS/Atom feeds. It can fetch full articles, run AI‑powered summarisation, translation, and content cleaning via any OpenAI‑compatible LLM, and re‑publish the result as a new RSS feed. Users define **AtomCrafts** (single steps) and combine them into **FlowCrafts** (pipelines), then save them as **Recipes** that expose custom RSS URLs. Deployment is Docker‑compose‑based, with optional Redis caching and a headless‑browser service for JavaScript‑heavy sites. Licensed under GPL‑v3.

  • Project
    fabriziosalmi/UglyFeed

    An LLM-powered application that retrieves, aggregates, and rewrites RSS feeds to create curated, high-quality content streams.

  • Project
    ziwenhahaha/daily-paper-reader

    A serverless AI paper discovery and reading system that automates personalized paper tracking and AI-powered summarization using GitHub Actions and Pages.