{"adoption": {"forks": 4586, "observed_at": "2026-08-28T04:12:11.139498+00:00", "stars": 46882}, "canonical_url": "https://ross.abutalabs.com/products/umi-ocr", "card": {"archived": false, "artifact_type": "application", "description": "OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。", "domain": ["computer-vision", "image-processing", "pdf", "developer-tools"], "enriched": true, "function": ["ocr", "image-processing", "pdf", "gui", "cli"], "health_score": 64, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["hiroi-sora/Umi-OCR"], "name": "hiroi-sora/Umi-OCR", "platform": ["windows", "cli"], "pushed_at": "2025-11-20T14:58:13+00:00", "repo": "hiroi-sora/Umi-OCR", "stars": 46882, "tags": ["offline-ocr", "screenshot-ocr", "batch-ocr", "qrcode", "paddleocr", "searchable-pdf", "http-api", "linux", "desktop"], "topics": ["paddleocr", "ocr", "ocr-python", "umi-ocr", "qml", "qt", "screenshot"], "urls": [], "use_cases": ["extract text from screenshots offline", "batch OCR a folder of images", "convert scanned PDFs to searchable PDFs", "recognize text without sending data to the cloud", "scan or generate QR codes", "call OCR from scripts via command line or HTTP API", "ignore watermarks and headers/footers when recognizing documents"], "what_it_is": "Umi-OCR is a free, open-source, fully offline OCR application for Windows and Linux with a Qt/QML GUI. It supports screenshot OCR, batch image recognition, PDF text extraction and searchable PDF generation, QR code scanning/generation, and CLI/HTTP interfaces for external calls.", "when_to_avoid": ["you need a library to embed in your own Python/JS code rather than a standalone app", "you need macOS or mobile support", "you need cloud-scale or GPU-cluster OCR throughput"], "when_to_choose": ["you need offline, privacy-preserving OCR on Windows or Linux", "you want batch processing of images or PDFs with layout handling", "you need an HTTP or CLI OCR service for automation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/umi-ocr", "repo": "hiroi-sora/Umi-OCR", "role": "main", "score": 47}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:11.139498+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:21:36.072902+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ece77b53895a464d74af8e9c23d8446bb6ad546fc86d7d951ee63b65f08037f4", "fetched_at": "2026-08-28T04:12:11.139498+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hiroi-sora/Umi-OCR"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 53, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1619, "days_push": 286, "days_rel": 526, "gap_med": null, "n_releases_24m": 1}, "score": 47, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}