Reusable AI skills and capabilities for agent workflows
ibmmobilecloud
Provides cognitive utilities to assist Hubot developers with deriving entities from statements.
febbyrg
A powerful PDF text and image extraction library with universal browser and Node.js support (Dual Licensed: Free for non-commercial, Paid for commercial use)
...moreflickzcode
News extraction and scraping. Article Parsing
juro-oravec
Production-ready web scraping in a single function call. Built on Crawlee. Data transforms, caching, privacy compliance, and error tracking -- out of the box.
...morepascalmartineau
WebSentry is a declarative web crawling and extraction framework.
mike-divinci
TypeScript port of Google's LangExtract — structured information extraction from text using LLMs with source grounding
ivicevic
Automated translation key extraction and dictionary management plugin for Next.js
guybraunstain
DynamoDB Data Transformation Tool
marcuth
Xcrap Extractor is a package of the Xcrap framework, it was developed to take care of the data extraction part of text files (currently supporting only HTML, JSON and Markdown) using declarative models.
...moredg_cpz
Semantic Understanding for Code Contexts — persistent memory for AI coding assistants (Claude Code, Cursor, Windsurf, Continue.dev)
...moresagold
json pointer - failsafe data retrieval from js and json objects
frankkulak
Models and functions for indexing and extracting files from the game.
sepehrf
A Node CLI tools for manipulating data. Handy for day-to-day Algolia SE work.
mozhn
Official TypeScript/JavaScript SDK for CrawlKit - the modern web scraping API. Scrape websites, extract structured data with AI, capture screenshots, and collect social media data.
...morecond
Capture and reuse authenticated browser sessions (Puppeteer + Playwright)
vmolinie
A CLI and toolkit to extract information from Ember components for documentation generation.
martinbaud
Natural language interface bridge between users and AeryFlux components
ebrimasamba
A react native android sms retriever api library for the new architecture
iambarryking
Zero-dependency TypeScript PDF text extraction for RAG and AI pipelines
tammilore
Intelligent document processing and extraction.
sami.mishal
Type-safe utility functions and type helpers for Drizzle ORM
meisterblack1211
JavaScript/Node.js port of NewPipeExtractor
monitz87
Data extraction module
GitHub Actions
Core types, configuration, and utilities for the Tally evaluation framework