firecrawl/anydoc

Health v2 · maintenance only

Flags: young

Adoption not part of the score

22812 stars · 1460 forks observed · 2026-10-14

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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.

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

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

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

Facets

library · maturity active

parser pdf csv markdown cli ocr files pdf developer-tools rust python wasm cli browser cross-platform document-conversion docx pptx xlsx epub odt rtf llm-ready github-flavored-markdown agent-skill natural-language-processing command-line nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="firecrawl/anydoc")