{"adoption": {"forks": 1077, "observed_at": "2026-08-28T04:11:26.780282+00:00", "stars": 18563}, "canonical_url": "https://ross.abutalabs.com/products/anydoc", "card": {"archived": false, "artifact_type": "library", "description": "Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.", "domain": ["files", "pdf", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "csv", "markdown", "cli", "ocr"], "health_score": 100, "homepage": "https://firecrawl.github.io/anydoc/", "language": "Rust", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["firecrawl/anydoc"], "name": "firecrawl/anydoc", "platform": ["rust", "python", "wasm", "cli", "browser", "cross-platform"], "pushed_at": "2026-08-24T21:30:12+00:00", "repo": "firecrawl/anydoc", "stars": 18563, "tags": ["document-conversion", "docx", "pptx", "xlsx", "epub", "odt", "rtf", "llm-ready", "github-flavored-markdown", "agent-skill", "natural-language-processing", "command-line", "nodejs"], "topics": [], "urls": [], "use_cases": ["convert docx files to markdown", "parse pdf documents into clean markdown for LLMs", "convert powerpoint and excel files to markdown", "batch convert office documents to github-flavored markdown", "run document conversion in the browser without uploading files", "convert documents to markdown from node.js or python", "prepare documents for RAG pipelines", "convert csv and epub files to markdown"], "what_it_is": "A fast Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF documents into clean GitHub-Flavored Markdown, with bindings for Node.js, Python, and the browser via WebAssembly. It normalizes all formats through a single document model and serializer, producing LLM-ready Markdown in single-digit milliseconds without ML models or external services.", "when_to_avoid": ["you need OCR for scanned PDFs (use Firecrawl Parse or another OCR tool instead)", "you need pixel-perfect fidelity to complex document layouts rather than clean Markdown", "you need conversion to formats other than Markdown"], "when_to_choose": ["you need fast, local, dependency-free conversion of office documents or text-based PDFs to Markdown", "you want one consistent Markdown output across many input formats", "you need bindings across Rust, Node.js, Python, CLI, and the browser", "you're feeding documents into LLM or RAG workflows"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/anydoc", "repo": "firecrawl/anydoc", "role": "main", "score": 79}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:26.780282+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:02:00.916387+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16f82eeba4f8f479cb21a519d9d9d6ed39a261e504ff7b877c519c9000953509", "fetched_at": "2026-08-28T04:11:26.780282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/anydoc"}, {"content_hash": "6debe5578a780738f049b7521471b025b71fa8d5a6c668c41ee40f7a45633ff4", "fetched_at": "2026-08-29T07:59:30.373212+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/anydoc/"}, {"content_hash": "6b50cc867078f4c5d7e4401321bfa18fe967d37859849e99d1b909b1ef1a308f", "fetched_at": "2026-08-29T07:59:30.375835+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/anydoc"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 2, "rhythm": 98}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 30, "days_push": 9, "days_rel": 13, "gap_med": 0.0, "n_releases_24m": 13}, "score": 79, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}