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
Pest Control Management Software
Pocomos is a cloud-based field service solution that caters to businesses
Built for the pest control industry, but also works great for Mosquito Control, Bin Cleaning, Window Washing, Solar Panel Cleaning, and other Home Service Businesses in need of an easy-to-use software that helps you simplify routing, scheduling, communications, payment processing, truck tracking, time tracking, and reporting.
WordNetLMF converts WordNet (http://wordnet.princeton.edu/) lexicographer files into KYOTO-LMF, the LMF dialect used in the KYOTO project (http://www.kyoto-project.eu/).
HTTP functional and non-functional (load and performance) toolkit based on jython/grinder (http://grinder.sf.net) ...includes capabilities to support: SOA services, REST, json/xml encoding, AES and WS security ... and a stub to collect requests
BibteXML is a bibliography schema for XML that expresses the content model of BibTeX – the bibliographic system for use with LaTeX. Stylesheets and conversion tools are provided.
Say goodbye to broken revenue funnels and poor customer experiences
Connect and coordinate your data, signals, tools, and people at every step of the customer journey.
LeanData is a Demand Management solution that supports all go-to-market strategies such as account-based sales development, geo-based territories, and more. LeanData features a visual, intuitive workflow native to Salesforce that enables users to view their entire lead flow in one interface. LeanData allows users to access the drag-and-drop feature to route their leads. LeanData also features an algorithms match that uses multiple fields in Salesforce.
The London Datastore (http://data.london.gov.uk) was created by the Greater London Authority (GLA) as an innovation towards freeing London’s data. This SourceForge Project will be used to Open Source our development efforts surrounding data formats
nexml is an xml format that represents phylogenetic data (trees, character sequence alignments, sets of OTUs, substitution models). The format is inspired by the commonly used flat-file NEXUS format, but more robust and easier to process.
An Inkscape extension for editable (digital) timing diagrams in publication quality, based on a very simple state-oriented language for signal description.
now here: https://github.com/plastex/plastex
plasTeX is a Python-based LaTeX document processing framework. It gives DOM-like access to a LaTeX document, as well as the ability to generate mulitple output formats (e.g. HTML, DocBook, tBook, etc.).
C4me aims to provide a convenient way of editing XML files (and, in a distant future, even more modding-related files) for modifications for Sid Meier's Civilization 4. It's now in its infancy and not really usable - join and help changing that!
Enterprises and companies seeking a solution to manage all their procurement operations and processes
eBuyerAssist by Eyvo is a cloud-based procurement solution designed for businesses of all sizes and industries. Fully modular and scalable, it streamlines the entire procurement lifecycle—from requisition to fulfillment. The platform includes powerful tools for strategic sourcing, supplier management, warehouse operations, and contract oversight. Additional modules cover purchase orders, approval workflows, inventory and asset management, customer orders, budget control, cost accounting, invoice matching, vendor credit checks, and risk analysis. eBuyerAssist centralizes all procurement functions into a single, easy-to-use system—improving visibility, control, and efficiency across your organization. Whether you're aiming to reduce costs, enhance compliance, or align procurement with broader business goals, eBuyerAssist helps you get there faster, smarter, and with measurable results.
La Madre es una revista de aparación esporadica de la agrupación estudiantil AMU. Su creación esta hecha completamente con Software Libre, utilizando principalmente Scribus.
This python script takes an exported wordpress xml file and outputs a single html document containing all posts in order of entry, and a table of contents broken down by Category. CSS tags added for easy formatting.
Notice: Citation Style Language (CSL) development has moved to https://github.com/citation-style-language/ (only the xbiblio-devel mailing list is still in use). For up to date information on CSL, visit the project home at CitationStyles.org.
A HTML scraper that uses machine learning frameworks to extract labelled fields from raw HTML. The project also involves the development of a tool to display the semi structured data generated by the scraper component.
SuperWillow is a Music Generation program. Artists have many influences which they have accumulated over the years by listening to countless pieces of music, this principle is reflected in SuperWillow.
This is a pure-Python XPath evaluator based on ElementTree. It supports a substantial fraction of the XPath 1.0 specification, but only the self, child, and attribute axes. The parser underlying the evaluator attempts to handle all of XPath 1.0.
BASIS FOR AN OPEN SOURCE PROJECT to convert NoteWorthy Composer files from/to MusicXML. Two Python 3 programs for NoteWorthy Composer files in nwctxt format. 1. nwctxt2xml.py - Converts nwctxt into XML 2. xml2nwctxt.py - Converts XML into nwctxt
Programming languages, software tools, and datasets for working with digital representations of diagrams in Ancient Science and Mathematics. Areas of focus for the project include navigation, production, assertion and querying of diagrammatic content.
BeyondRSS is an off-line RSS reader. It allows user to download and archive the contents of RSS links, so these pages can be read without connecting to Internet.
Software to translate the geographical format SOSI into KML or other spatial data formats. SOSI is the Norwegian National format for exchange of spatial data.
Planetary Scale Event Propagation and Router ("PsEPR" pronounced "pepper") is an experimental status and notification service. Pub/sub system for exchange of XML messages creating an event service for PlanetLab (http://www.planet-lab.org/).