Self-host papernews
0.1.0News aggregator rendering feeds into calm LaTeX PDF digests
- Stars
- 165
- Storage
- ~2 GB of disk for the image
- Port
- 8000 (HTTP web server serving landing page and PDF digest)
What is papernews?
papernews aggregates news from RSS/Atom feeds and Hacker News, extracts full article text with trafilatura, then uses an LLM backend (Anthropic API or a local Ollama instance) to summarize and rewrite each article into clean, translated English. The results are rendered via a Jinja LaTeX template into a multi-page PDF with a magazine-style layout: cover page with quote of the day and world news, table of contents, and two-column article bodies with proper typography. The PDF is served on-demand from a Flask web server (port 8000) and cached. Ingest runs on a schedule (every 4 hours by default or at fixed times). All data lives in a local SQLite database and cached PDFs on a bind-mounted volume. It runs via Docker Compose or a local Python 3.11+ virtual environment with TeX Live installed. The project is a hobby project with rough edges expected.
Should you self-host papernews?
papernews scores 38/100 on selfhost.directory (how scoring works) and ranks #72 of 85 in Feed Reader. It has 165 GitHub stars.
There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.
Setup is moderate: expect some configuration beyond a single command. It is MIT-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is RSSHub (85/100, 46 702 stars). It scores higher overall, so compare the two before you pick. See papernews vs RSSHub side by side.
Features
- Anthropic Claude API support
- Automatic translation to English
- Did you know trivia
- Hacker News aggregation
- LaTeX PDF generation
- LLM-powered article rewriting
- LLM-powered article summarization
- Offline-first reading
- On-demand PDF rendering with caching
- Post-ingest delivery hooks
- reMarkable/e-ink optimization
- RSS/Atom Feed Aggregation
- Scheduled background ingestion
- World news and quote of the day
papernews README
More in Document Processing
PDFMathTranslateSelf-hosted, open-source scientific PDF translator that preserves formulas, tables and layout, via CLI, Gradio GUI or Docker using Google, DeepL, Ollama or OpenAI.
Receipt Parser ServerSelf-hosted, open-source receipt parser server that uses Tesseract OCR to extract structured data from receipt images via a REST API with token authentication.
Resume-MatcherSelf-hosted, open-source AI resume builder that tailors a master resume to each job description with Ollama or any major LLM provider, then exports ATS-friendly PDFs.
RigorousRigorous is a self-hosted, open-source Python tool using 24 AI agents to analyze academic manuscripts with detailed feedback and PDF reports.
RowfillSelf-hosted open-source agentic tables platform for document extraction, deep research, and AI data processing.
SnapOtterOpen-source, self-hosted file-processing suite with 200+ image, video, audio, PDF and document tools, local AI, a REST API and pipelines.
Stirling-PDFStirling PDF is a self-hosted, open-source PDF editor with 60+ tools for editing, signing, redacting, converting, and automating PDFs. Runs via Docker or JAR.
textsnaptextsnap is a self-hosted OCR CLI extracting text from images, screenshots, URLs, and webpages using local CPU models with no GPU or cloud required.
TypstOpen-source, self-hosted markup typesetting system: a CLI and Rust library that compiles Typst files to PDF, PNG, SVG, or HTML as an easier alternative to LaTeX.
unstructuredSelf-hosted open-source REST API for document partitioning into structured elements as JSON/CSV. Supports PDF, images, OCR, table extraction, chunking.
Apache TikaOpen-source toolkit that extracts text and metadata from 1000+ file types, with a self-hosted REST or gRPC server for search indexing and LLM/RAG pipelines.
BentoPDFOpen-source, self-hosted PDF toolkit with 100+ browser-based tools to merge, split, edit, convert, OCR and sign PDFs - files never leave your device.
0 comments