{"adoption": {"forks": 461, "observed_at": "2026-08-28T04:09:45.853711+00:00", "stars": 6635}, "canonical_url": "https://ross.abutalabs.com/products/monkeyocr", "card": {"archived": false, "artifact_type": "library", "description": "A lightweight LMM-based Document Parsing Model", "domain": ["artificial-intelligence", "computer-vision", "pdf", "deep-learning"], "enriched": true, "function": ["ocr", "pdf", "machine-learning", "llm-inference", "image-processing"], "health_score": 76, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Yuliang-Liu/MonkeyOCR"], "name": "Yuliang-Liu/MonkeyOCR", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-20T13:41:34+00:00", "repo": "Yuliang-Liu/MonkeyOCR", "stars": 6635, "tags": ["document-parsing", "multimodal", "vision-language-model", "layout-analysis", "pdf-to-markdown", "natural-language-processing", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["parse pdf documents into markdown", "extract text and tables from scanned documents", "ocr for academic papers with formulas", "convert document images to structured text", "multilingual document parsing", "batch document digitization pipeline"], "what_it_is": "MonkeyOCR is a lightweight large multimodal model (LMM) for document parsing that uses a Structure-Recognition-Relation triplet paradigm to convert documents (including PDFs and images) into structured text like Markdown. It provides pretrained model weights, a Python inference pipeline, and a demo, with an active v2 release line.", "when_to_avoid": ["you need only plain OCR without layout or structure understanding", "you have no GPU and need fast lightweight processing", "you need a fully managed cloud OCR API"], "when_to_choose": ["you need open-source document parsing with layout, text, formula, and table recognition", "you want a lightweight multimodal OCR model with pretrained weights", "you need multilingual document extraction in Python"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/monkeyocr", "repo": "Yuliang-Liu/MonkeyOCR", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.853711+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:43:12.751789+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c747050f096781b952ca64cb7362c928283e3c746351de2ad65370dc482211a", "fetched_at": "2026-08-28T04:09:45.853711+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Yuliang-Liu/MonkeyOCR"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 32, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 456, "days_push": 44, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}