Open Source Packages
Libraries, frameworks, tools, and SDKs used by the apps in this directory — scored the same way as the apps themselves.
All Packages
Category
Tags2
Sort:Used by Most Apps
pypdf
A pure-Python library for splitting, merging, cropping, transforming, and extracting content from PDF files.
pdf-parse
Pure TypeScript PDF parser for extracting text, images, tables, and metadata in Node.js and browsers.
Partial JSON
Parses incomplete JSON strings streamed token-by-token from an LLM into usable JavaScript values as they arrive.
officeParser
Parse Office documents into a rich AST and generate Markdown, HTML, PDF, or RAG chunks
schema-dts
TypeScript type definitions for Schema.org's JSON-LD vocabulary, giving structured data literals full autocomplete and compile-time validation.
PaddleOCR
Multilingual OCR and document-parsing toolkit that turns PDFs and images into structured data.
pdf-inspector
Fast Rust library for PDF classification, text extraction, and Markdown conversion
LiteParse
Fast, open-source PDF and document parser with Python bindings, OCR, and spatial text extraction.
baml
The Python runtime for BAML — a typed prompt language that compiles LLM calls into type-safe, testable client code.
Llama Cloud Services
Python SDK for LlamaCloud's document parsing, extraction, and managed index services
LlamaParse
GenAI-native document parser that turns complex files into LLM-ready text and Markdown.
Partial JSON Parser
A zero-dependency Python library that completes and parses incomplete JSON streamed token-by-token from LLMs.