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
Atera all-in-one platform IT management software with AI agents
Ideal for internal IT departments or managed service providers (MSPs)
Atera’s AI agents don’t just assist, they act. From detection to resolution, they handle incidents and requests instantly, taking your IT management from automated to autonomous.
The OO-Browser is an advanced object-oriented class browser with
support for browsing C, C++, Common Lisp and its Object System
(CLOS), Eiffel, Java, Objective-C, Python and Smalltalk. It runs
atop Emacs/XEmacs on Linux, UNIX and Windows.
This is a small program that enable you to generate XML from your 'home made' document format (should be a text file...) following a very simple control file.
The FastForm is a component that helps a user to fill out huge forms and only fields that needed wasting no time to look up proper fields through the whole form.
Jess-mode is a collection of Emacs Lisp files designed to facilitate the development of Java Expert System Shell (JESS) applications. Currently, the package consists of a major mode for editing source and an inferior mode used to run the Jess interpreter
Java library for Schema based file parser.
Csv and flat file parser and writer.
This is a java library that enables to parse and write Csv and flat files based on a schema.
Pure java syntax highlighting.
The project lets you add syntax highlighting to your projects.
You can create your own custom syntax files so you can customize it to your needs and add it to your java-based projects.
Lightspeed Golf is all-in-one golf course management software to help courses simplify operations, drive revenue and deliver amazing golf experiences.
From tee sheet management, point of sale and payment processing to marketing, automation, reporting and more—Lightspeed is built for the pro shop, restaurant, back office, beverage cart and beyond.
This project starts to create an open tool for creating, manipulating and visualizing DTDs (in a later state it should work also with other other specification languages such as XML Schema and RELAX NG).
DOX is a document processing system inspired by TeX, but much more lightweight and simple to use. DOX keeps the source text as simple as possible by replacing obscure formatting symbols and constructs with more "natural" alternatives.
A knowledgment management system written in Java under JBoss 4.2.3 Server, with richfaces 3.3.0BETA4. Including fileconversion from html to pdf and rich:editor component without special syntaxing.
An experimental set of tools for text analysis and dictionary construction. One goal is to improve text-input e.g. on devices with touchscreens using dictionary-based symbolic on-screen keyboards.
TX is a free and open source cross-platform Computer Assisted Translation tool with translation memory, full and partial matches, machine translation, glossaries, search engine, support for various document types, and translation projects.
This is a new Yaml loader, reader, writer and preprocessor API, with a UTF-8 Encoding support and more. See YamlPreprocessor Github Page <https://github.com/SparkPowered/YamlPreprocessor/> for more.
Integrated environment for the modelling and simulation of process control systems, where the plant(s) are described according to the Modelica object-oriented paradigm, while the control systems are specified in an IEC 61131.3-compliant language.
Trison has the goal to become a template engine with support of php, java and the transform ability to javascript to intergrate client/serverside generation of code.
A software tool to discover the names of people in electronic documents and HTML markup, note the use of the work 'discover' rather than search. Using this tool, the association bewteen names in documents can be inferred.