{"adoption": {"forks": 2826, "observed_at": "2026-08-28T04:12:07.808461+00:00", "stars": 39295}, "canonical_url": "https://ross.abutalabs.com/products/marker", "card": {"archived": false, "artifact_type": "library", "description": "Convert PDF to markdown + JSON quickly with high accuracy", "domain": ["pdf", "files", "machine-learning", "developer-tools"], "enriched": true, "function": ["ocr", "pdf", "parser", "machine-learning", "llm-inference"], "health_score": 100, "homepage": "https://www.datalab.to", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["datalab-to/marker"], "name": "datalab-to/marker", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-26T21:36:48+00:00", "repo": "datalab-to/marker", "stars": 39295, "tags": ["pdf-to-markdown", "document-conversion", "document-intelligence", "deep-learning", "ocr", "gpu"], "topics": [], "urls": [], "use_cases": ["convert pdf to markdown", "extract text and tables from scanned pdfs", "turn documents into json for llm ingestion", "ocr pdfs with equations and math", "batch convert docx and pptx to markdown", "prepare documents for rag pipelines", "extract images from pdf documents"], "what_it_is": "Marker is a Python library and CLI tool that converts PDFs, images, and office documents (DOCX, PPTX, XLSX, EPUB, HTML) into markdown, JSON, HTML, and chunks with high accuracy. It uses deep learning models for layout detection and OCR, with optional LLM-boosted accuracy, and runs on GPU, CPU, or MPS.", "when_to_avoid": ["you only need simple text extraction from born-digital PDFs (pdftotext may suffice)", "you cannot run deep learning models locally and don't want the managed platform", "you need pixel-perfect visual fidelity rather than structured markdown output"], "when_to_choose": ["you need fast, accurate pdf-to-markdown conversion at scale", "your documents contain tables, math, forms, or multi-column layouts", "you want a self-hosted alternative to managed document APIs", "you need to feed documents into LLM or RAG workflows"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/marker", "repo": "datalab-to/marker", "role": "main", "score": 92}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.808461+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:24:10.905619+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0f6465b71e0b5f3d5f26594aab57551810693fa6a7adc857f30fec8ef98617d3", "fetched_at": "2026-08-28T04:12:07.808461+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/marker"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:46:47.144810+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 74, "rhythm": 93}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1038, "days_push": 7, "days_rel": 44, "gap_med": 3.0, "n_releases_24m": 59}, "score": 92, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}