{"adoption": {"forks": 2389, "observed_at": "2026-08-28T04:12:07.618257+00:00", "stars": 38671}, "canonical_url": "https://ross.abutalabs.com/products/tesseractjs", "card": {"archived": false, "artifact_type": "library", "description": "Pure Javascript OCR for more than 100 Languages 📖🎉🖥", "domain": ["computer-vision", "image-processing", "web-development"], "enriched": true, "function": ["ocr", "image-processing", "nlp"], "health_score": 86, "homepage": "http://tesseract.projectnaptha.com/", "language": "JavaScript", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["naptha/tesseract.js"], "name": "naptha/tesseract.js", "platform": ["browser", "wasm", "cross-platform"], "pushed_at": "2026-05-17T04:19:12+00:00", "repo": "naptha/tesseract.js", "stars": 38671, "tags": ["tesseract", "webassembly", "text-recognition", "multilingual", "bounding-boxes", "natural-language-processing", "nodejs", "javascript"], "topics": ["tesseract", "webassembly", "ocr", "javascript", "deep-learning"], "urls": [], "use_cases": ["extract text from images in the browser", "ocr scanned documents with javascript", "recognize text in multiple languages from photos", "run ocr on node.js server without native binaries", "get word and character bounding boxes from an image", "real-time text recognition from video frames"], "what_it_is": "Tesseract.js is a pure JavaScript port of the Tesseract OCR engine that extracts text from images in over 100 languages. It runs in the browser (via script tag, webpack, or CDN) and on Node.js, supporting automatic orientation/script detection and word/character bounding boxes.", "when_to_avoid": ["you need maximum OCR accuracy on complex documents - native Tesseract or cloud OCR services may perform better", "you need handwriting recognition or modern deep-learning-based OCR quality", "performance on very large batch jobs is critical - native implementations are faster"], "when_to_choose": ["you need client-side OCR without a backend or native dependencies", "you need multilingual text recognition across 100+ languages", "you want bounding box data for words, paragraphs, or characters", "you want a well-maintained, widely used OCR library for JavaScript"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tesseractjs", "repo": "naptha/tesseract.js", "role": "main", "score": 70}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:07.618257+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:24:50.141451+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e43cb8d56c8e711bdad03fc6f2281df4f04ffe0bc53d697e90793f1a722f235", "fetched_at": "2026-08-28T04:12:07.618257+00:00", "kind": "readme", "missing": false, "url": "https://github.com/naptha/tesseract.js"}, {"content_hash": "8b42fabf1e02e05b18629f111918a31dfd0daaa7c6ce8ef91ecddd308565dfd8", "fetched_at": "2026-08-29T07:47:09.407631+00:00", "kind": "homepage", "missing": false, "url": "http://tesseract.projectnaptha.com/"}, {"content_hash": "ba3ff4f4457a5ffeb43ea63d5ed7db7763a5da19404c2cc30f1d7c61133b8af7", "fetched_at": "2026-08-29T07:47:09.410167+00:00", "kind": "registry_npm", "missing": false, "url": "https://registry.npmjs.org/tesseract.js"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 82, "longevity": 100, "rhythm": 37}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4088, "days_push": 108, "days_rel": 261, "gap_med": 170.0, "n_releases_24m": 3}, "score": 70, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}