#3636th of 60 in Data and scraping for AI
sumy
Extractive text summarizer for web pages and plain text, as library and CLI
- Stars
- 3.7k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Aug 2026
- Language
- Python
3,655 on 22 Apr 20263,700 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Sumy is a Python library and command line tool that summarizes HTML pages (by URL) or plain text by selecting key sentences with classic extractive algorithms such as LexRank, Luhn, LSA and Edmundson. It also includes a small evaluation framework for scoring summaries against a reference. It uses no neural or LLM models.
Who it is for: Python developers needing model-free extractive summaries of text or web pages
Strengths
- Installs with pip or uv; usable as a library or via sumy and sumy_eval commands
- Several extractive algorithms (LexRank, Luhn, LSA, Edmundson) with per-language tokenizers
- Built-in evaluation commands compare summaries against a reference text
- Docker image and a Hugging Face Space allow trying it without installing
Weaknesses
- Extractive only: picks existing sentences, cannot rewrite or abstract
- Language coverage depends on tokenizers; unsupported languages need manual additions
- Python API example still carries legacy Python 2 compatibility imports
What it needs
- no GPU
- Docker
What changed
- v0.13.0 ↗ (opens in a new tab)Security fix
CVE-2024-39705, GHSA-CX63-2MW6-8HW5, GHSA-5RJG-FVGR-3XXF. “INCOMPATIBILITY: nltk>=3.9 is now required, since 3.8.2 withdrew the punkt pickle over CVE-2024-39705. See https://github.com/miso-belica/sumy/issues/216”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Data and scraping for AI
See all 60| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 91 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 89 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |