44 packages matching “pymupdf”
vecpdf
v0.0.1 · 1 year ago
CLI tool to process PDFs and create local vector databases using ChromaDB
No known vulnerabilities
pdf-compare
v2026.8.17 · 1 month ago
Compare two PDF files and generate a visual diff report with highlighted differences
No known vulnerabilities
chem-pdf2ppt
v2.1.0 · 4 months ago
Convert chemistry academic paper PDFs into professional PowerPoint & HTML presentations. Auto-detects paper type (experimental/theoretical/hybrid), extracts figures via caption-guided + vector + embedded multi-strategy, generates structured slides with La
No known vulnerabilities
pdf-tools-mcp
v0.3.5 · 1 year ago
PDF Tools MCP server with OCR capabilities - Convert PDFs to images, extract text with OCR, extract images, and metadata
No known vulnerabilities
dsh-docintel
v0.3.0 · 1 month ago
Personal document knowledge base for DeepSeek Harness: add any PDF/Markdown/text file into a local SQLite FTS5 store with page-level locators, search it with Chinese-friendly retrieval, and get page-cited answers from the agent. Web drawer included (v0.2)
No known vulnerabilities
opencode-plugin-office
v0.1.2 · 2 months ago
opencode plugin: office_read/office_edit/office_create/office_render/office_python tools for .docx/.pptx files, plus the office-tools skill.
No known vulnerabilities
@nalinor/mupdf4llm
v0.2.0 · 4 months ago
TypeScript port of pymupdf4llm — convert PDFs to LLM-ready Markdown using the mupdf WASM package.
No known vulnerabilities
paper-agent-cli
v0.1.3 · 1 month ago
An AI agent that reads research PDFs (via mupdf.js) and extracts field, method, result, and impact — with compare, benchmark, methodology-figure, and code-generation commands.
No known vulnerabilities
rag-playground-skill
v1.0.0 · 5 months ago
Claude Code skill for benchmarking RAG configurations — upload docs, compare chunking/embeddings/vector stores in 5 minutes
No known vulnerabilities
pdf2wiki
v0.2.0 · 2 months ago
收集多家公司产品PDF, 自动结构化成统一内部检索Wiki(LLM结构化+几何配图+并发+多公司聚合)
No known vulnerabilities
turbo-parsepdf-wasm
v0.1.1 · 3 months ago
PDF text/table/image extraction in the browser via WebAssembly — wasm-bindgen binding for turbo-parsepdf-core.
No known vulnerabilities
@moziaverse/ocr-cli
v0.7.0 · 1 month ago
支持图片和多页 PDF 的 OpenAI 兼容 OCR 命令行工具
No known vulnerabilities
@leettools/web
v3.0.0 · 1 month ago
Web search, scraping, and crawling utilities for LeetTools.
No known vulnerabilities
dsh-document-evidence
v0.2.0-beta.9 · 13 days ago
Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web
No known vulnerabilities
turbo-parsepdf
v0.1.1 · 3 months ago
Fast native PDF text/table/image extraction for Node — pure-Rust core, HTML/Markdown/JSON output.
No known vulnerabilities
ragparser
v1.0.1 · 1 month ago
Ragparser.com SDK for parsing PDFs
No known vulnerabilities
@pdfmuse/node
v0.1.12 · 1 month ago
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
No known vulnerabilities
@pdfmuse/node-win32-x64-msvc
v0.1.12 · 1 month ago
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
No known vulnerabilities
@pdfmuse/node-darwin-arm64
v0.1.12 · 1 month ago
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
No known vulnerabilities
@pdfmuse/node-darwin-x64
v0.1.12 · 1 month ago
Deterministic PDF/DOCX parser for RAG / LLMs — native Node.js binding.
No known vulnerabilities