{"adoption": {"forks": 136, "observed_at": "2026-08-28T04:04:58.794915+00:00", "stars": 1531}, "canonical_url": "https://ross.abutalabs.com/products/docstrange", "card": {"archived": false, "artifact_type": "library", "description": "Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.", "domain": ["pdf", "files", "artificial-intelligence", "developer-tools"], "enriched": true, "function": ["ocr", "pdf", "parser", "nlp", "machine-learning", "llm-inference", "rag", "data-science"], "health_score": 50, "homepage": "https://docstrange.nanonets.com/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["NanoNets/docstrange"], "name": "NanoNets/docstrange", "platform": ["python", "windows", "cli"], "pushed_at": "2025-10-31T14:00:01+00:00", "repo": "NanoNets/docstrange", "stars": 1531, "tags": ["document-conversion", "document-parsing", "pdf-to-markdown", "structured-data-extraction", "table-extraction", "document-ai", "mcp-server", "web-ui", "cloud-api", "local-processing", "natural-language-processing", "data-engineering", "linux", "macos", "web-server", "gpu"], "topics": ["image-to-markdown", "llm", "markdown", "ocr", "pdf-to-markdown", "structured-data", "ai", "document-parser", "document-parsing", "pdf-parser", "pdf-to-json", "structured-data-capture", "tables"], "urls": [], "use_cases": ["convert pdf to markdown for llm ingestion", "extract tables from scanned pdfs into", "ocr images and turn text into structured data", "parse word and powerpoint documents into markdown", "extract specific fields from documents given a  schema", "prepare rag-ready clean text from messy documents", "batch convert documents offline without sending data to the cloud"], "what_it_is": "DocStrange is a Python library and tool that converts documents (PDF, DOCX, PPTX, XLSX, images, URLs) into Markdown, JSON, CSV, or HTML using advanced OCR and a 7B vision-language model. It supports both a free cloud API and fully local processing, includes a built-in web UI, and offers an MCP server for Claude Desktop integration.", "when_to_avoid": ["you only need simple text extraction from plain-text or well-structured HTML files", "you cannot run a 7B model locally and cannot use cloud processing for privacy reasons", "you need a lightweight pure-Python parser with no ML model dependencies"], "when_to_choose": ["you need high-accuracy document-to-markdown conversion with table extraction", "you want a choice between free cloud processing and 100% private local mode", "you need structured extraction against a JSON schema from mixed document types", "you want an alternative to docling, marker, or markitdown with OCR built in"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/docstrange", "repo": "NanoNets/docstrange", "role": "main", "score": 40}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.794915+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:21.646878+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "23a83853e0511d4b7688ede488ef7e118fae133162f934b3abd02d1b883989ea", "fetched_at": "2026-08-28T04:04:58.794915+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NanoNets/docstrange"}, {"content_hash": "3b474da30d6c93a21fd003817c4bc6f17890d7e109dc51379f4454f65ffc7b13", "fetched_at": "2026-08-29T11:33:37.803439+00:00", "kind": "homepage", "missing": false, "url": "https://docstrange.nanonets.com/"}, {"content_hash": "4dddab6c78de0a08882194513b4ace2cfbe214e386a1bde6690d520d7d526bb7", "fetched_at": "2026-08-29T11:33:37.806101+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docstrange/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 49, "longevity": 28, "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": 398, "days_push": 306, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 40, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}