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
G-P - Global EOR Solution
Companies searching for an Employer of Record solution to mitigate risk and manage compliance, taxes, benefits, and payroll anywhere in the world
With G-P's industry-leading Employer of Record (EOR) and Contractor solutions, you can hire, onboard and manage teams in 180+ countries — quickly and compliantly — without setting up entities.
KNN-WEKA provides a implementation of the K-nearest neighbour algorithm for Weka. Weka is a collection of machine learning algorithms for data mining tasks. For more information on Weka, see http://www.cs.waikato.ac.nz/ml/weka/.
NESD-Imaging is a 2D rendering framework for Java. It combines JAI and Java2D and extends them by providing lazy rendering (do not block UI). It provides geo-positionned images rendering (à la google-map). It scales well to large image set (>500GB).
The main goal of OWLVE is to visualize graphically any OWL–lite file. Using powerful RCP and GEF technologies will improve the quality of graphics and diagrams.This project includes an algorithm for similarity calculus between two OWL files.
This application talks to a GPS device over the NMEA protocol via the WIGSGPSComm API. The first version of the WIGS application will present the GPS data in an intuitive fashion, and later releases will be further enhanced with special map support.
dbt Labs empowers data teams to build reliable, governed data pipelines—accelerating analytics and AI initiatives with speed and confidence.
Data teams use dbt to codify business logic and make it accessible to the entire organization—for use in reporting, ML modeling, and operational workflows.
basE91 is an advanced method for encoding binary data as ASCII characters. It is similar to UUencode or base64, but is more efficient. The overhead produced by basE91 depends on the input data. It amounts at most to 23% and can range down to 14%.
Open Source IM and voice client using Jabber and SIP protocols, with great audio quality thanks to speex and a nice and clean interface. Programmed in Java and C++. It supports chat, voice and file transfers.
Java Component created to persist and work with trees (it doesn't matter the type of persistence). Based on "Nested Set Model of Hierarchies" by Joe Celko. [Componente Java para persistir y trabajar con árboles (no importa el tipo de persistencia)]
This project intends to create an indexing search engine, for knowledge management. The primary object is to apply an information retrieval core. And implement a knowledge data discovery theory such as data mining algorithm, text mining.
OAP Lite is Optimized Algorithms Platform Lite, which simplifies the process of solving some optimization problems by Genetic Algorithms. It is a highly configurable, efficient tool for user to get the optimum result without programming.
Rezku is an all-inclusive ordering platform and management solution for all types of restaurant and bar concepts. You can now get a fully custom branded downloadable smartphone ordering app for your restaurant exclusively from Rezku.
SenseRank Sys:
- builds the dictionaries (multidim matrices) of words’ values;
- for the set utterance in certain language builds a figure in multidimensional space (in the matrix space) of values (visual schema), which is topological view of sense
A Java implementation of the NEAT algorithm as created by Kenneth O Stanley. Also provides a toolkit for further experiments to be created and can provide both local and distributed learning environments.
Meaningful acronym and name generator from a list of keywords provided by the user. The software checks that the random words generated exist in the specified language by checking against a spelling engine publicy available as a web service
The K.U.Leuven JCHR System is an integration of Constraint Handling Rules (CHR) and Java designed with three aims in mind: user-friendliness, flexibility and efficiency.
http://www.cs.kuleuven.be/~petervw/JCHR/
SMSCompress is a project of investigation, development and implementation of different SMS compression techniques.
Using these techniques, SMS of more than 160 characters can be sent at only one SMS, saving money to the user ;)
XMLMath evaluates mathematical, logical or textual expressions described in xml and prints the result. For example, to compute the result of 1 + 1, you would write: <add> <long value="1"/> <long value="1"/> </add>
RAS is the acronym for Result Assessment System. The primary purpose of RAS is helping users manage, visualize, assess and report results obtained from experimental search algorithms.
StrMatch is a simple java program, created for educational purposes, that allows user to test a great part of string matching algorithms.
An intuitive user interface shows each algorithm step accurately...