{"adoption": {"forks": 848, "observed_at": "2026-08-28T04:10:52.200031+00:00", "stars": 12266}, "canonical_url": "https://ross.abutalabs.com/products/zerox", "card": {"archived": false, "artifact_type": "library", "description": "OCR & Document Extraction using vision models", "domain": ["pdf", "artificial-intelligence", "large-language-models", "developer-tools", "files"], "enriched": true, "function": ["ocr", "pdf", "llm-inference", "machine-learning", "data-science"], "health_score": 43, "homepage": "https://getomni.ai/ocr-demo", "language": "TypeScript", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["getomni-ai/zerox"], "name": "getomni-ai/zerox", "platform": ["python", "cross-platform"], "pushed_at": "2025-05-20T00:39:18+00:00", "repo": "getomni-ai/zerox", "stars": 12266, "tags": ["vision-models", "document-extraction", "markdown-output", "openai", "gemini", "aws-bedrock", "document-ai", "nodejs"], "topics": ["ocr", "pdf"], "urls": [], "use_cases": ["convert pdfs to markdown for llm ingestion", "extract text from scanned documents using vision models", "ocr documents with weird layouts and tables", "parse docx and image files into markdown", "extract structured data from documents with a schema", "prepare documents for rag pipelines"], "what_it_is": "Zerox is a library (Node.js and Python packages) that performs OCR and document extraction by converting files like PDFs, DOCX, and images into page images and sending them to vision models (GPT-4o, Gemini, Bedrock, etc.) to produce Markdown. It supports schema-based data extraction, concurrent page processing, and format maintenance across pages.", "when_to_avoid": ["you need fully offline or free OCR without LLM API costs", "you require pixel-perfect text extraction where hallucination is unacceptable", "you need high-volume batch processing with minimal latency and cost", "you need a traditional OCR engine like Tesseract"], "when_to_choose": ["you need markdown output from complex document layouts, tables, or charts", "you want to leverage multimodal LLMs instead of traditional OCR engines", "you need support for multiple model providers (OpenAI, Azure, Bedrock, Gemini)", "you're building AI ingestion or RAG pipelines over documents"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/zerox", "repo": "getomni-ai/zerox", "role": "main", "score": 35}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:52.200031+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:14:12.497460+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5731f1d547188a93fb08d13555c262826b26fbdeedabab7848f54f1da8e2e58", "fetched_at": "2026-08-28T04:10:52.200031+00:00", "kind": "readme", "missing": false, "url": "https://github.com/getomni-ai/zerox"}, {"content_hash": "7b01d8633b96682effe477c5d21468ac52565aec2406bdac907d0cd95af94ff3", "fetched_at": "2026-08-29T08:11:56.042460+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/zerox"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 22, "longevity": 55, "rhythm": 40}, "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": 773, "days_push": 471, "days_rel": 623, "gap_med": 2, "n_releases_24m": 8}, "score": 35, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}