{"adoption": {"forks": 162, "observed_at": "2026-08-28T04:05:29.141945+00:00", "stars": 1736}, "canonical_url": "https://ross.abutalabs.com/products/sitefetch", "card": {"archived": false, "artifact_type": "cli-tool", "description": "Fetch an entire site and save it as a text file (to be used with AI models).", "domain": ["developer-tools", "large-language-models", "crawlers"], "enriched": true, "function": ["web-scraping", "cli", "nlp"], "health_score": 21, "homepage": null, "language": "TypeScript", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["egoist/sitefetch"], "name": "egoist/sitefetch", "platform": ["cli", "cross-platform"], "pushed_at": "2025-01-18T05:30:04+00:00", "repo": "egoist/sitefetch", "stars": 1736, "tags": ["site-crawler", "readability", "llm-context", "typescript", "command-line", "nodejs"], "topics": [], "urls": [], "use_cases": ["scrape a whole website into one text file for LLM context", "fetch only blog and docs pages from a site", "extract readable content from web pages for AI models", "crawl documentation sites to feed into a chatbot", "convert a website to plain text offline"], "what_it_is": "A Node.js CLI tool that crawls an entire website and saves its pages as a single text file, using Mozilla Readability to extract clean content. It is designed to prepare site content as context for AI/LLM models.", "when_to_avoid": ["you need JavaScript-rendered SPA content at scale", "you need structured data exports like JSON or CSV", "you need a full-featured scraping framework with scheduling or proxies"], "when_to_choose": ["you need a site's content as plain text for AI model input", "you want a quick zero-config CLI crawler with glob page matching", "you want readable-content extraction with optional CSS selectors"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/sitefetch", "repo": "egoist/sitefetch", "role": "main", "score": 22}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.141945+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:30:40.918117+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "faca90372fcfb81f836075769fdc9def0fd355bcfe408e1865a6c48cde654b5e", "fetched_at": "2026-08-28T04:05:29.141945+00:00", "kind": "readme", "missing": false, "url": "https://github.com/egoist/sitefetch"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 2, "longevity": 43, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 603, "days_push": 592, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 22, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}