# steipete/summarize

Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.

Repository: https://github.com/steipete/summarize
Canonical: https://ross.abutalabs.com/products/summarize
Homepage: https://summarize.sh
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, cli, summarize, typescript
Last push: 2026-08-23T08:07:28+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 18
- inputs: {"age_days": 259, "days_push": 10, "days_rel": 23, "gap_med": 1.0, "n_releases_24m": 45}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6577, forks 442 (observed 2026-08-28T04:09:45.355795+00:00)

## What it is
Summarize is a Node.js CLI and Chrome/Firefox extension that extracts clean text from web pages, PDFs, YouTube videos, podcasts, and audio/video files, then produces LLM-generated summaries. It runs a real extraction pipeline (Readability, markitdown, yt-dlp, Whisper, Firecrawl) before handing content to any configured model provider.

## Use cases
- summarize a YouTube video from its transcript
- extract clean readable text from a web page for piping into scripts
- transcribe a podcast episode and get a summary
- summarize a local PDF or audio file
- extract slides and OCR text from a recorded talk
- get a quick gist of any URL from the terminal
- batch-summarize conference videos with an agent

## When to choose
- you need one tool that handles URLs, PDFs, YouTube, podcasts, and media transcripts
- you want provider-agnostic LLM summaries including local models via Ollama
- you need clean extraction without any LLM or API key (--extract mode)
- you want stable JSON output for automation and pipes

## When to avoid
- you need a GUI-first summarization workflow rather than CLI/browser extension
- you only want simple article extraction without media or LLM features
- you cannot install Node.js 24+ or optional media tools like ffmpeg and yt-dlp

## Facets
- artifact type: cli-tool
- maturity: active
- function: nlp, ocr, speech-recognition, web-scraping, llm-inference, cli, pdf, developer-tools
- domain: developer-tools, media, artificial-intelligence
- platform: windows, cli, browser-extension, cross-platform
- tags: summarization, content-extraction, youtube-transcripts, podcast-transcription, readability, whisper, chrome-side-panel, llm-providers, natural-language-processing, command-line, automation, macos, linux, nodejs

## Member repositories
- steipete/summarize (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.355795+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:43:37.252447+00:00, confidence not recorded.
  - readme: https://github.com/steipete/summarize (fetched 2026-08-28T04:09:45.355795+00:00, sha cd75cad62d14)
  - homepage: https://summarize.sh (fetched 2026-08-29T08:40:27.439143+00:00, sha 36ac37603889)
  - site_page: https://summarize.sh/docs/install.html (fetched 2026-08-29T08:40:27.441915+00:00, sha 8287cd7db7c4)
  - site_page: https://summarize.sh/docs/quickstart.html (fetched 2026-08-29T08:40:27.443833+00:00, sha 2242b13ec290)
  - site_page: https://summarize.sh/docs/config.html (fetched 2026-08-29T08:40:27.445519+00:00, sha edea4bfa769e)
  - site_page: https://summarize.sh/docs/website.html (fetched 2026-08-29T08:40:27.447399+00:00, sha 08c36e13f6c2)
  - site_page: https://summarize.sh/docs/youtube.html (fetched 2026-08-29T08:40:27.448968+00:00, sha 85602b101d4d)
  - site_page: https://summarize.sh/docs/media.html (fetched 2026-08-29T08:40:27.450788+00:00, sha 98ce7618eb2d)
  - site_page: https://summarize.sh/docs/extract-only.html (fetched 2026-08-29T08:40:27.452752+00:00, sha 52caf94d5b42)
  - site_page: https://summarize.sh/docs/slides.html (fetched 2026-08-29T08:40:27.455085+00:00, sha 44a3aa9afaf7)
- Data as of 2026-08-30T08:39:29.467469+00:00.