{"adoption": {"forks": 2395, "observed_at": "2026-08-28T04:12:00.637883+00:00", "stars": 34589}, "canonical_url": "https://ross.abutalabs.com/products/ocrmypdf", "card": {"archived": false, "artifact_type": "cli-tool", "description": "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["ocr", "pdf", "image-processing", "cli"], "health_score": 99, "homepage": "http://ocrmypdf.readthedocs.io/", "language": "Python", "license": "MPL-2.0", "license_family": "copyleft", "maturity": "stable", "member_repos": ["ocrmypdf/OCRmyPDF"], "name": "ocrmypdf/OCRmyPDF", "platform": ["windows", "python", "cli", "cross-platform"], "pushed_at": "2026-08-22T03:30:49+00:00", "repo": "ocrmypdf/OCRmyPDF", "stars": 34589, "tags": ["tesseract", "pdfa", "scanned-documents", "searchable-pdf", "deskew", "batch-processing", "command-line", "linux", "macos", "docker"], "topics": ["python", "ocr", "pdf", "image-processing", "tesseract"], "urls": [], "use_cases": ["make scanned pdfs searchable", "add ocr text layer to pdf", "convert scanned documents to searchable pdf/a", "deskew and clean crooked pdf scans", "batch ocr thousands of pages", "ocr pdfs in multiple languages", "extract text from scanned pdfs"], "what_it_is": "OCRmyPDF is a Python command-line tool that adds an OCR text layer to scanned PDF files using Tesseract, making them searchable and copy-pasteable. It produces validated PDF/A output with image preprocessing options like deskew, rotation correction, and optimization across multiple CPU cores.", "when_to_avoid": ["you need a GUI-based OCR workflow", "you want to OCR non-PDF documents like Word or plain images without conversion", "you need handwriting recognition, which Tesseract handles poorly"], "when_to_choose": ["you need a scriptable, battle-tested CLI for OCRing PDFs at scale", "you want PDF/A output with lossless text-layer insertion", "you need multilingual OCR with 100+ Tesseract languages", "you want image preprocessing like deskew and rotation fixes built in"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ocrmypdf", "repo": "ocrmypdf/OCRmyPDF", "role": "main", "score": 98}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.637883+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:27:28.422681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a3280a168ffddc1f2e1241e84fa0ba45864dedb015136f7a0b65ac02fbbd50", "fetched_at": "2026-08-28T04:12:00.637883+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocrmypdf/OCRmyPDF"}, {"content_hash": "53d7a424306c2aa29c1c96fabfb66f9b47a0b9d5b43794b24b8c6f5c8ce68428", "fetched_at": "2026-08-29T07:48:12.275419+00:00", "kind": "homepage", "missing": false, "url": "http://ocrmypdf.readthedocs.io/"}, {"content_hash": "19142297622b4ef50585d2d86bb28fb750761702eadc6effad2e6cbe25dff011", "fetched_at": "2026-08-29T07:48:12.284675+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/ocrmypdf/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 96}, "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": 4639, "days_push": 11, "days_rel": 29, "gap_med": 11.5, "n_releases_24m": 29}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}