{"adoption": {"forks": 173, "observed_at": "2026-09-01T02:14:05.024554+00:00", "stars": 1061}, "canonical_url": "https://ross.abutalabs.com/products/mittagessen-kraken", "card": {"archived": false, "artifact_type": "library", "description": "OCR engine for all the languages", "domain": ["computer-vision", "pdf", "files"], "enriched": true, "function": ["ocr", "machine-learning", "image-processing", "nlp"], "health_score": 100, "homepage": "http://kraken.re", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["mittagessen/kraken"], "name": "mittagessen/kraken", "platform": ["python", "cli"], "pushed_at": "2026-08-30T10:55:32+00:00", "repo": "mittagessen/kraken", "stars": 1061, "tags": ["handwritten-text-recognition", "htr", "layout-analysis", "pagexml", "alto-xml", "hocr", "historical-documents", "non-latin-scripts", "neural-networks", "natural-language-processing", "linux", "macos"], "topics": ["ocr", "neural-networks", "alto-xml", "hocr", "handwritten-text-recognition", "htr", "layout-analysis", "optical-character-recognition", "page-xml"], "urls": [], "use_cases": ["recognize text in historical manuscripts", "OCR for non-Latin scripts like Arabic or Hebrew", "transcribe handwritten documents", "extract text from scanned images into PageXML or ALTO", "binarize and segment scanned page images", "train custom OCR models for rare scripts", "handle right-to-left and bidirectional text in OCR"], "what_it_is": "kraken is a turn-key OCR/HTR engine built on neural networks, optimized for historical and non-Latin script material. It provides trainable layout analysis, reading order detection, and multi-script character recognition with output in ALTO, PageXML, abbyyXML, and hOCR formats.", "when_to_avoid": ["you need a plug-and-play OCR for modern Latin-script documents with no training", "you want a GUI-based OCR tool", "you need Windows support", "you want commercial support or prebuilt binaries outside pip"], "when_to_choose": ["you need OCR for historical, damaged, or non-Latin script material", "you want fully trainable recognition and layout analysis models", "you need structured output formats like ALTO, PageXML, or hOCR", "you work with right-to-left, BiDi, or vertical scripts", "you need both printed text and handwritten text recognition"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mittagessen-kraken", "repo": "mittagessen/kraken", "role": "main", "score": 99}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-01T02:14:05.024554+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:56:58.335527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc60770dd748e2ec2d9aab627e970cb96232025444905051abd063cf61115fc8", "fetched_at": "2026-09-01T02:14:05.024554+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mittagessen/kraken"}, {"content_hash": "08f06ae12298be455e6de76cf3714b599d4fcf05a7c63bf669653e9db3e3e3c0", "fetched_at": "2026-08-29T12:59:05.427625+00:00", "kind": "homepage", "missing": false, "url": "http://kraken.re"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 100, "longevity": 100, "rhythm": 96}, "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": 4124, "days_push": 3, "days_rel": 28, "gap_med": 17, "n_releases_24m": 10}, "score": 99, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 5, "stale_scrape": false}}