Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Retrieve, aggregate, filter, evaluate, rewrite and serve RSS feeds using Large Language Models for fun, research and learning purposes
| Date | Stars |
|---|---|
| 2026-07-31 | 315 |
| 2026-08-01 | 315 |
| 2026-08-06 | 315 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# <img src="https://raw.githubusercontent.com/fabriziosalmi/UglyFeed/main/docs/UglyFeed.png" alt="UglyFeed" height="32" width="32"> UglyFeed UglyFeed is a **simple** application designed to **retrieve**, **aggregate**, **filter**, **rewrite**, **evaluate** and **serve** content (RSS feeds) written by a large language model. This repository provides the [code](https://github.com/fabriziosalmi/UglyFeed.git), the **[documentation](https://github.com/fabriziosalmi/UglyFeed/blob/main/docs/README.md)**, a [FAQ](https://github.com/fabriziosalmi/UglyFeed/blob/main/docs/faq.md), a [troubleshooting guide](https://github.com/fabriziosalmi/UglyFeed/blob/main/docs/troubleshooting.md), and some optional scripts to evaluate the generated content.   [](https://github.com/fabriziosalmi/UglyFeed/actions/workflows/pylint.yml) [](https://github.com/fabriziosalmi/UglyFeed/actions/workflows/github-code-scanning/codeql)    ## Features - 📡 Retrieve RSS feeds - 🧮 Aggregate feeds items by similarity - ✨ Rewrite content using LLM API - 💾 Save rewritten feeds to JSON files - 🔁 Convert JSON to valid RSS feed - 🌐 Serve XML feed via HTTP server - 🌎 Deploy XML feed to GitHub or GitLab - 📈 Evaluate generated content - 🖥️ Web UI based on Streamlit - 📰 [RSS test feeds available](https://github.com/fabriziosalmi/uglyfeed-cdn) - 🤖 Same codebase for all releases - 🛑 Simple post-filter moderation - ➡️ [Translate feeds](https://github.com/fabriziosalmi/UglyFeed/blob/main/prompts/translate.txt) into your own language - 📝 Tons of [prompts](https://github.com/fabriziosalmi/UglyFeed/tree/main/prompts) ready to use ## Get it now - 💾 [Source code](https://github.com/fabriziosalmi/UglyFeed/releases/latest) - 🐳 [Docker installable package](https://hub.docker.com/r/fabriziosalmi/uglyfeed) - 🐍 [Pip installable package](https://pypi.org/project/uglypy/) - ⚙️ [Github actions workflows](https://github.com/fabriziosalmi/UglyFeed/blob/main/docs/README.md#%EF%B8%8F-installation-and-automated-runs-github-actions) ## Quick start ### Prerequisites - 🌎 Internet connection - 🐳 Docker - ✨ LLM API - 📲 RSS reader **Supported API and models** - OpenAI API (`gpt-3.5-turbo`, `gpt-4`, `gpt-4o`) - Ollama API (all models like `llama3`, `phi3`, `qwen2`) - Groq API (`llama3-8b-8192`, `llama3-70b-8192`, `gemma-7b-it`, `mixtral-8x7b-32768`) - Anthropic API (`claude-3-haiku-20240307`, `claude-3-sonnet-20240229`, `claude-3-opus-20240229`) - Google Gemini API (Free tier: `gemini-2.0-flash`, `gemini-2.0-flash-lite`, `gemini-1.5-flash`, `gemini-1.5-flash-8b`, `gemma-3`, `gemma-3n`) > You can use your own models by running a compatible OpenAI LLM server. You must change the OpenAI API url parameter. ### Running the Container To start the UglyFeed app, use the following `docker run` command: ```bash docker run -p 8001:8001 -p 8501:8501 -v /path/to/local/feeds.txt:/app/input/feeds.txt -v /path/to/local/config.yaml:/app/config.yaml fabriziosalmi/uglyfeed:latest ``` ### Configure the application In the **Configuration** page (or by manually editing the `config.yaml` file) you will find all configuration options. You must change at least the source feeds you want to aggregate, the LLM API and model to use to rewrite the aggregated feeds. You can then retrieve the final `uglyfeed.xml` feed in many ways: - local filesy
Excerpt of 9,434 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:810f81676dd37fb6, topic:llm