Crawl websites, sync to vector databases, and power RAG applications. Pre-built integrations for LLM pipelines and AI assistants.
Build data pipelines that feed your AI models and agents without managing infrastructure. Crawl any website, transform content, and push directly to your preferred vector store. Use 10,000+ tools for RAG applications, AI assistants, and real-time knowledge bases. Monitor site changes, trigger workflows on new data, and keep your AIs fed with fresh, structured information. Cloud-native, API-first, and free to start until you need to scale.
Try for free
The Original Buy Center Software.
Never Go To The Auction Again.
VAN sources private-party vehicles from over 20 platforms and provides all necessary tools to communicate with sellers and manage opportunities. Franchise and Independent dealers can boost their buy center strategies with our advanced tools and an experienced Acquisition Coaching™ team dedicated to your success.
ZML, the Zeitung Markup Language, is a simple CMS for small newspapers. It was specifically designed to publish a student newspaper in print and on the Web. It uses LaTeX and XHTML. So far, it is documented in German only.
A simple Gedit Plugin which enables a markup syntax to produce extended characters. 59 defaults but extra character support can be added easily making this plugin highly configurable.
Dun and Bradstreet Connect simplifies the complex burden of data management
Our self-service data management platform enables your organization to gain a complete and accurate view of your accounts and contacts.
The amount, speed, and types of data created in today’s world can be overwhelming. With D&B Connect, you can instantly benchmark, enrich, and monitor your data against the Dun & Bradstreet Data Cloud to help ensure your systems of record have trusted data to fuel growth.
WikiPDF is a mediawiki extension based on Wiki2PDF that adds PDF/LaTeX features to mediawiki. Wiki2PDF is a python script to convert multiple articles of a mediawiki based wiki (pre-configured to use with www.wikipedia.org) to a single LaTeX or PDF file.
Typewriter converts plain text files to PDF. It allows users to create underlined text and superscript. The PDF created looks exactly as the text, with the same line and page breaks, allowing users the simplicity and control of a typewriter.
rpl is a text replacement utility. It will replace strings with new strings in multiple text files. It can work recursively over directories and supports limiting the search by file suffixes. This version was originally written by Göran Weinholt.
pyfiglet is a full port of the FIGlet specification (http://www.figlet.org/) into pure python. It takes ASCII text and renders it in ASCII art fonts. It can be used on the commandline or as an Object Oriented driver library in your own programs.
Have you ever encountered dynamic web page (php, asp.net...) problems as like being browsed full of question marks? This (currently) tiny utility is for you. It tries to correct the problem by changing the file encoding to unicode.
SE|PY is an ActionScript editor written in python, wxPython and using scintilla for text highlight, code collapsing. some features: snippets panel, functions panel and much more.
Contain also Flush
This script converts books from the open Gutenberg project base text format into a format easily readable by an iPod's notes feature.
This project is written in Python and is so accessible across many Operating systems.
SilverCity is a lexing package, based on Scintilla, that can provide lexical analysis for over 20 programming and markup langauges. Scripting language bindings currently exist for Python.
The project is intended to be a text preproccesor that works using user-generated xml files describing certain rules to be applied. It's thought for general use on any text file where a pattern can be specified to apply an "xml rule" over it.
The software Tabua is a very, very simple python script code for table creation and manipulation. It is intended to be an easy way to build, change, manipulate and extract tables in many (language) formats.
A Python-based template and view-controller framework derived from HTML::Mason. Supports the full featureset of Mason, allowing component-based web development with Python-embedded HTML, and includes many new concepts and features not found in Mason.
A student of the Franklin W. Olin College of Engineering wrote his own extremely customizeable, extraordinarily functional, tabbed text editor in Python and pygtk. Works on windows and POSIX-compliant systems. For the scripter and excessive customizer.