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 csvdatamix project aims to randomize CSV input data files in order to conceal the original state of the data. Similar to data masking or data transformation. Also has mapping abilities to translate back to the original state of the data.
SAADA transforms a set of heterogeneous astronomical data FITS files in a powerfull database deployed on the Web and including VO features. The database is located on your host and keeps under your full control. This job doesn't require to write cod
This is an advanced web scraper with user friendly GUI which let the user define rules and web addresses to extract data from one time or periodically and a target database filed that the data should be saved in.
A project to make a simple, but complete, bibtex parser using regexes in Java. It is meant as a library for a larger program, and so is not interactive. Testers, contributors, comments and suggestions are more than welcome.
The goal of this project is to provide a Content Provider plugin for the iQser GIN Platform (www.iqser.com) as a semantic middleware to synchronize and transform data objects of any Social Community supporting the Open Social standard.
Incredable is the first DLT-secured platform that allows you to save time, eliminate errors, and ensure your organization is compliant all in one place.
For healthcare Providers and Facilities
Incredable streamlines and simplifies the complex process of medical credentialing for hospitals and medical facilities, helping you save valuable time, reduce costs, and minimize risks. With Incredable, you can effortlessly manage all your healthcare providers and their credentials within a single, unified platform. Our state-of-the-art technology ensures top-notch data security, giving you peace of mind.
Text and basic html renderer. Useful to read text/html files in mp3/mp4 devices using its photo/image viewer . Comes with default settings for a sansa fuze mp4 player. It needs a Perl interpreter, but is provided one in-pack for windows.
Tibco EMS Message Admin allows you to purge a queue, list messages in a queue, save a message from a queue to a file, edit the message in memory and send to another (or same) queue, load message from a file and send it to a queue.
JACo XML is a handy, tiny component designed to help you with your work with XMLs in Java. The idea is to see every XML as an object instance and then work with it.
A Python script that can be used to get information on TV shows and Movie Shows from thetvdb.org and themoviedb.org. This is an learning experience and anybody can chime in on everything.
pngacidbath is the one true PNG image brute force compressor. While other tools simply run down a list of "intelligent" compressor algorithms (some known as zlib methods), pngacidbath tries every byte combination to come up with THE smallest file.
The Universal Batch Converter is a project to take all the myriad file conversion programs, and provide a powerful but easy to use interface for all types of file conversion.
The Java Calendar Tools project will contain opensource components for use in Calendar applications. The focus will be on providing tools that are in compliance with existing standards like iCal (RFC 2445).
POP - Persistent Objects for PHP - is a library intended to make simple ORM for the main databases existent in the market - PostgreSQL, MS SQL, Oracle and MySQL. Complete OO and making use of PDO, it also secures your project against SQL Injection
PekiLine is a personal English vocabulary designed to learning. Words are translated on-line using a Google dictionary include a pronunciation. The application stores all searched words in the local XML file for more learning.