{"adoption": {"forks": 210, "observed_at": "2026-08-28T04:03:57.394284+00:00", "stars": 1197}, "canonical_url": "https://ross.abutalabs.com/products/calamari", "card": {"archived": false, "artifact_type": "library", "description": "Line based ATR Engine based on OCRopy", "domain": ["computer-vision", "image-processing", "developer-tools"], "enriched": true, "function": ["ocr", "machine-learning", "deep-learning", "cli"], "health_score": 83, "homepage": null, "language": "Python", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["Calamari-OCR/calamari"], "name": "Calamari-OCR/calamari", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-06-23T22:11:57+00:00", "repo": "Calamari-OCR/calamari", "stars": 1197, "tags": ["ocr-engine", "ocropy", "kraken", "tensorflow", "handwritten-text-recognition", "historical-documents", "line-based-ocr", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["recognize text in scanned historical documents", "train a custom OCR model for old prints", "run OCR on line images from the command line", "integrate OCR into a Python digitization pipeline", "recognize handwriting in manuscripts", "ensemble multiple OCR models for better accuracy"], "what_it_is": "Calamari is a Python-based OCR engine for line-based automatic text recognition, built on OCRopy and Kraken with a TensorFlow deep-learning backend. It offers both a command-line interface and a modular Python API, with pretrained models available for many historical scripts.", "when_to_avoid": ["you need general-purpose document layout analysis out of the box", "you want a GUI-based OCR tool", "you need OCR for modern documents where Tesseract suffices"], "when_to_choose": ["you need trainable, high-accuracy OCR for historical or non-Latin scripts", "you want a scriptable Python OCR engine with pretrained models", "you work with line-segmented images from OCRopy/Kraken pipelines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/calamari", "repo": "Calamari-OCR/calamari", "role": "main", "score": 74}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.394284+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:21:16.635570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9485e4f4c77719d110e7d7b91c508afba5aa62b8107e986f922018237058560", "fetched_at": "2026-08-28T04:03:57.394284+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Calamari-OCR/calamari"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 89, "longevity": 100, "rhythm": 40}, "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": 3088, "days_push": 71, "days_rel": 659, "gap_med": 20.5, "n_releases_24m": 3}, "score": 74, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}