{"adoption": {"forks": 275, "observed_at": "2026-08-28T04:08:36.222680+00:00", "stars": 4137}, "canonical_url": "https://ross.abutalabs.com/products/chunkr", "card": {"archived": false, "artifact_type": "service", "description": "Vision infrastructure to turn complex documents into RAG/LLM-ready data", "domain": ["artificial-intelligence", "pdf", "developer-tools"], "enriched": true, "function": ["ocr", "parser", "rag", "machine-learning", "pdf", "api-framework"], "health_score": 80, "homepage": "https://chunkr.ai", "language": "Rust", "license": "AGPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["lumina-ai-inc/chunkr"], "name": "lumina-ai-inc/chunkr", "platform": ["self-hosted", "rust", "python"], "pushed_at": "2026-04-09T22:53:39+00:00", "repo": "lumina-ai-inc/chunkr", "stars": 4137, "tags": ["document-intelligence", "layout-analysis", "semantic-chunking", "document-parsing", "llm-data-preparation", "vision-language-models", "retrieval-augmented-generation", "natural-language-processing", "docker", "web-server"], "topics": [], "urls": [], "use_cases": ["parse pdfs into rag-ready chunks", "extract structured text from scanned documents with ocr", "convert word docs and powerpoints for llm ingestion", "chunk complex documents semantically for vector search", "self-host a document parsing pipeline", "get bounding boxes and layout structure from documents"], "what_it_is": "Chunkr is an open-source document intelligence API that performs layout analysis, OCR, and semantic chunking to convert PDFs, presentations, Word documents, and images into RAG/LLM-ready structured data. It is a production-ready service deployable via Docker Compose, with a separate managed cloud API offering proprietary models.", "when_to_avoid": ["you need maximum parsing accuracy without infrastructure work - the managed cloud API uses proprietary in-house models", "you need a permissive license - the open-source version is AGPL-3.0", "you only need simple plain-text extraction from clean PDFs"], "when_to_choose": ["you need to feed complex documents into RAG or LLM pipelines", "you want a self-hosted, production-ready document parsing service", "you need OCR plus layout analysis with structured HTML/Markdown output"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chunkr", "repo": "lumina-ai-inc/chunkr", "role": "main", "score": 55}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:36.222680+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:23:00.849639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c662864c1e3538a77ed0ee92d2b80ad8532f42e805323d2d3839e86df56acc13", "fetched_at": "2026-08-28T04:08:36.222680+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lumina-ai-inc/chunkr"}, {"content_hash": "5ac3f2ff6068d71c91059788e5ac279020438e7311041a662f0c6c5959bb21b3", "fetched_at": "2026-08-29T09:14:02.556396+00:00", "kind": "homepage", "missing": false, "url": "https://chunkr.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 76, "longevity": 52, "rhythm": 29}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 739, "days_push": 146, "days_rel": 398, "gap_med": 0, "n_releases_24m": 118}, "score": 55, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}