{"adoption": {"forks": 63, "observed_at": "2026-08-28T04:04:57.794569+00:00", "stars": 1521}, "canonical_url": "https://ross.abutalabs.com/products/documind", "card": {"archived": false, "artifact_type": "library", "description": "Open-source platform for extracting structured data from documents using AI.", "domain": ["artificial-intelligence", "large-language-models", "pdf", "files", "developer-tools"], "enriched": true, "function": ["ocr", "parser", "pdf", "llm-inference", "nlp", "machine-learning"], "health_score": 44, "homepage": "https://www.documind.xyz", "language": "JavaScript", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["DocumindHQ/documind"], "name": "DocumindHQ/documind", "platform": ["cross-platform", "cli"], "pushed_at": "2025-05-15T07:57:08+00:00", "repo": "DocumindHQ/documind", "stars": 1521, "tags": ["document-extraction", "structured-data", "pdf-to-", "schema-driven-extraction", "llm", "openai", "local-llm", "markdown-conversion", "natural-language-processing", "nodejs"], "topics": ["ai", "document-extraction", "llms", "open-source", "pdf-extractor", "developer-tools", "ocr", "document-analysis", "extract-data", "parser", "pdf", "pdf-converter", "pdf-extractor-llm"], "urls": [], "use_cases": ["extract structured data from pdf documents", "parse bank statements into", "convert pdfs to markdown", "auto-generate extraction schemas from documents", "run document extraction with local llms", "extract fields from invoices or receipts with a custom schema"], "what_it_is": "Documind is an open-source Node.js library that uses AI/LLMs to extract structured JSON data from PDFs and other documents based on customizable schemas. It supports OpenAI as well as local vision models (Llava, Llama3.2-vision) and converts documents to Markdown.", "when_to_avoid": ["you need a fully managed hosted extraction API without self-setup", "you require a non-AGPL license for commercial embedding", "you need high-throughput OCR without LLM costs"], "when_to_choose": ["you need schema-driven structured JSON output from unstructured documents", "you want an npm library that works with OpenAI or local vision models", "you need multi-format support (PDF, DOCX, PNG, JPG, TXT, HTML)"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/documind", "repo": "DocumindHQ/documind", "role": "main", "score": 33}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:57.794569+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:49.944460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0224b699fc22abdbf0eee7e603f2a57e0d4aaa6bacc9b1b2636f3a9df0c05bd7", "fetched_at": "2026-08-28T04:04:57.794569+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DocumindHQ/documind"}, {"content_hash": "6f672c44033363774c987a7a4b634cd4d74e6e974906e3bda81be2938a362e5f", "fetched_at": "2026-08-29T11:35:03.047388+00:00", "kind": "homepage", "missing": false, "url": "https://www.documind.xyz"}, {"content_hash": "89c6e590681fa3d3bad49aae9b0ce4909083258d57e13799830c9c81493af6a1", "fetched_at": "2026-08-29T11:35:03.057475+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/documind"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 21, "longevity": 46, "rhythm": 40}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 655, "days_push": 475, "days_rel": 558, "gap_med": 7.0, "n_releases_24m": 9}, "score": 33, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}