Turn any document (PDF, Word, Excel, PowerPoint, OpenDocument, HTML, JSON, CSV, text) into agent-ready markdown, typed blocks, and metadata — one call, with an optional custom-parser hook for vision LLMs and bespoke formats.
Faithful DOCX renderer with exposed typed IR for building document editors
Independent community DeepSeek Harness plugin for secure multi-file upload, native images, local document retrieval, and coordinate-aware text/PDF/DOCX/XLSX/PPTX reading.
A dead simple docx parser.
MCP server for reading, writing and converting LibreOffice & Office documents — pure JS, no external dependencies required
Production-ready MCP server for document ingestion and knowledge management with vector search. Supports PDF, DOCX, TXT, MD, CSV, JSON, HTML with ChromaDB and multiple embedding providers.
Enterprise Document Intelligence Engine — Core Package
Extend MDAST by parsing embedded HTML in Markdown. Converts HTML into structured MDAST nodes compatible with @m2d/core for DOCX generation.
MCP server for generating and parsing Word/PDF/Excel/PowerPoint documents using docxtpl
AI-powered CV/Resume parser with multi-provider support (Gemini, OpenAI, Claude)
A NodeJS library to parse pdf, txt, doc and docx files to JSON and CSV
Finds the number of occurrences of one or more phrases in a directory of .doc, .docx, and .pdf files.
This npm package offers a straightforward method to extract text content from various binary and text file formats. The package comes with a pre-built configuration that works out-of-the-box, requiring no additional setup. It is designed for use in Browse
typescript docx parser
MCP server that reads documents as Markdown and creates or edits DOCX files
Node.js client for the Resume Reader API: parse PDF, DOCX and scanned resumes into 114 structured JSON fields, and normalize job titles, skills and locations.
Yet another library to extract text from MS Office and PDF files
Parse a SIG / CAIQ / VSA / VSAQ security questionnaire (xlsx, docx, pdf, csv) into structured JSON. Ingest + normalize + framework detection only — no answers, no auto-fill.
A NodeJS library to parse pdf, txt, doc and docx files to JSON and CSV
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
Simple DOCX/DOC document parser powered by LlamaParse v2
Client-side Office Open XML (DOCX) editor and parser engine for browsers and Node.js. Official open-source client for Free DOCX Editor by UCDREAMS (https://ucdreams.com).
Power Document Extractor – universal local document parser for n8n
读取任意文件格式 - Excel、CSV、Word、图片、PDF,本地解析 + AI 识别,支持并发
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
Parse multiple-choice exam items from DOCX (marker template) and XLSX files, in the browser or Node.
Full-featured document parsing node for n8n — PDF, DOCX, XLSX, PPTX, images, OCR, markdown output. No native dependencies.
A composable, pipeline-based data ingestion toolkit for Next.js and Node.js projects. Parse, chunk, transform, validate, and store data from any source.
Convert it! The ultimate file conversion toolkit. Convert, extract, analyze, search, and process PDFs, Word docs, Excel spreadsheets, images, and more with a powerful, chainable API. Supports batch processing, streaming, and intelligent document analysis.
> **Note** > This repository is automatically generated from the [main parser monorepo](https://github.com/TrialAndErrorOrg/parsers). Please submit any issues or pull requests there.
The Structured Parser JS/TS SDK allows developers to easily integrate Structured Parser's advanced structured data extraction capabilities from unstructured documents such as PDF, DOCX, XLSX.
A simple library that converts .docx files to plain text in the browser
File parser registry for Dornick. Lazy VFS sub-mounts under /user/files//parsed/*. Built-in CSV/JSON/text; companion packages add PDF, DOCX, XLSX, OCR, ML, audio.
AI-powered CV parsing widget for recruitment portals
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.