summarize

CLI

Link → clean text → summary.

A pragmatic pipeline for the web: extract the good stuff, sanitize it, then summarize with your model of choice.

Website extraction YouTube transcripts JSON + metrics

Extraction that’s not naive

HTML → normalized text, with fallbacks when a site fights back.

Cheerio + sanitization + optional Firecrawl

YouTube transcripts, without drama

Pull captions via multiple paths so “missing transcript” becomes rare.

Website vs YouTube modes

Built for pipelines

--extract-only, --json, and --metrics make it scriptable.

Compose it with your own tools

Provider-agnostic LLMs

OpenAI, xAI, Gemini — use what you’ve got, pin what you need.

Control via --model + env vars