{"adoption": {"forks": 787, "observed_at": "2026-08-28T04:10:42.419654+00:00", "stars": 10578}, "canonical_url": "https://ross.abutalabs.com/products/pymupdf", "card": {"archived": false, "artifact_type": "library", "description": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.", "domain": ["pdf", "files", "data-science", "developer-tools"], "enriched": true, "function": ["pdf", "ocr", "parser", "image-processing", "nlp"], "health_score": 100, "homepage": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs", "language": "Python", "license": "AGPL-3.0", "license_family": "copyleft", "maturity": "stable", "member_repos": ["pymupdf/PyMuPDF", "pymupdf/pymupdf4llm"], "name": "PyMuPDF", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T11:53:06+00:00", "repo": "pymupdf/PyMuPDF", "stars": 10578, "tags": ["mupdf", "text-extraction", "table-extraction", "llm-rag", "document-conversion", "epub", "xps", "natural-language-processing"], "topics": ["mupdf", "xps", "pdf-documents", "epub", "ocr", "pdf", "font", "python", "data-science", "extract-data", "table-extraction", "pymupdf", "tesseract", "text-processing", "text-shaping"], "urls": [{"kind": "homepage", "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}], "use_cases": ["extract text from pdf files in python", "convert pdfs to markdown for llm and rag pipelines", "extract tables from pdf documents", "perform ocr on scanned pdfs with tesseract", "render pdf pages to images", "manipulate and annotate pdf documents programmatically"], "what_it_is": "PyMuPDF is a high-performance Python library built on the MuPDF C engine for extracting, analyzing, converting, rendering, and manipulating PDF and other document formats. Its companion package pymupdf4llm provides utilities for converting documents into LLM/RAG-friendly output like Markdown.", "when_to_avoid": ["your project cannot accept AGPL-3.0 licensing and you cannot buy a commercial license", "you only need to create simple PDFs from scratch rather than process existing documents", "you need a pure-Python solution without a compiled C engine"], "when_to_choose": ["you need fast, dependency-light PDF text and image extraction in Python", "you are building document ingestion pipelines for LLMs or RAG systems", "you need table extraction, OCR, or page rendering from PDFs", "you need low-level control over PDF structure alongside high-level APIs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/pymupdf/PyMuPDF", "repo": "pymupdf/PyMuPDF", "role": "main", "score": 98}, {"path": "/repos/pymupdf/pymupdf4llm", "repo": "pymupdf/pymupdf4llm", "role": "plugin", "score": 82}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.419654+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:18:30.920130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e70b6bf8ae7da5e9464f3dab7a08b60f1071688c724558d951a86a9e0029eaf9", "fetched_at": "2026-08-28T04:10:42.419654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pymupdf/PyMuPDF"}, {"content_hash": "69176eac07142559982d70534869f8be88f793defe82228ca48428131bfdeb77", "fetched_at": "2026-08-29T08:17:41.851008+00:00", "kind": "homepage", "missing": false, "url": "https://pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs"}, {"content_hash": "af6627c88bad0fe96d20e74cd7d48bbc8d8960539f17989d627e685f50805d60", "fetched_at": "2026-08-29T08:17:41.860261+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pymupdf4llm/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": 5079, "days_push": 7, "days_rel": 27, "gap_med": 26.0, "n_releases_24m": 23}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}