{"adoption": {"forks": 47, "observed_at": "2026-08-28T04:03:51.949416+00:00", "stars": 1173}, "canonical_url": "https://ross.abutalabs.com/products/doc7", "card": {"archived": false, "artifact_type": "cli-tool", "description": "Turn documents into AI-ready Markdown with visual understanding", "domain": ["pdf", "files", "developer-tools", "artificial-intelligence", "large-language-models"], "enriched": true, "function": ["ocr", "pdf", "markdown", "image-processing", "llm-inference", "nlp"], "health_score": 98, "homepage": null, "language": "Go", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["magicrew/doc7"], "name": "magicrew/doc7", "platform": ["cli", "windows", "cross-platform", "go"], "pushed_at": "2026-08-07T12:08:40+00:00", "repo": "magicrew/doc7", "stars": 1173, "tags": ["document-ai", "pdf-to-markdown", "docx-to-markdown", "vision-language-model", "multimodal", "local-ai", "openai-compatible", "rag-preprocessing", "macos", "linux"], "topics": ["document-ai", "docx-to-markdown", "local-ai", "markdown", "multimodal", "open-source", "pdf-to-markdown", "vision-language-model"], "urls": [], "use_cases": ["convert pdf to markdown for llm ingestion", "extract text from scanned pdfs without ocr", "prepare documents for rag pipelines", "convert docx to markdown", "parse charts and formulas from pdfs into markdown", "run document conversion locally with a private vision model"], "what_it_is": "doc7 is a Go CLI tool that converts PDFs, Office files, scans, screenshots, charts, formulas, and diagrams into AI-ready Markdown using any OpenAI-compatible multimodal vision-language model, including local deployments via Ollama or LM Studio. It requires no OCR stack and rebuilds multi-page documents into a single searchable Markdown output.", "when_to_avoid": ["you need a pure-text extraction pipeline with no LLM dependency", "you have no access to an OpenAI-compatible multimodal model endpoint", "you need pixel-perfect fidelity to original document formatting", "you need batch conversion at scale with minimal compute cost"], "when_to_choose": ["you need AI-ready Markdown from complex or raster-only documents", "you want local/private processing with your own multimodal model", "you want to avoid OCR stacks or per-page document-parser fees", "you need to preserve figures, equations, and layout structure in Markdown"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/doc7", "repo": "magicrew/doc7", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.949416+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:28:23.826884+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33f4274d1d1e3972248185ad1e2d21c56dcecf5b918fc8e1c856a342bda6ef08", "fetched_at": "2026-08-28T04:03:51.949416+00:00", "kind": "readme", "missing": false, "url": "https://github.com/magicrew/doc7"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 2, "rhythm": 96}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 31, "days_push": 26, "days_rel": 26, "gap_med": 2.0, "n_releases_24m": 3}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}