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
Nonprofit Budgeting Software
Martus Solutions provides seamless budgeting, reporting, and forecasting tools that integrate with accounting systems for real-time financial insights
Martus' collaborative and easy-to-use budgeting and reporting platform will save you hundreds of hours each year. It's designed to make the entire budgeting process easier and create unlimited financial transparency.
The next version of Kneemail will be released through the Google open source project hosting service. The SourceForge project is being closed. We will update this info once the next release has been made public. kneemail@kneemailcentral.com
TCL/TK based browser of a Latex project, aims to
- parse .tex files to create call tree / label list / toc
- interact with compiler (latex/pdflatex), editors and viewers (xdvi/pdf)
Cloud data warehouse to power your data-driven innovation
BigQuery is a serverless and cost-effective enterprise data warehouse that works across clouds and scales with your data.
BigQuery Studio provides a single, unified interface for all data practitioners of various coding skills to simplify analytics workflows from data ingestion and preparation to data exploration and visualization to ML model creation and use. It also allows you to use simple SQL to access Vertex AI foundational models directly inside BigQuery for text processing tasks, such as sentiment analysis, entity extraction, and many more without having to deal with specialized models.
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.
ASCIIMathML.js: a JavaScript to convert ASCII math notation (and some LaTeX) to Presentation MathML while your webpage loads. Now also simple graphs are translates to SVG. Works with Firefox 2.0+ or with Internet Explorer 6/7+MathPlayer+Adobe SVGview.
Open Office Server Daemon based on older daemon written in python (oood).
Open Office is unstable as a server (memory leaks, not multithreaded, ...), this daemon makes it working in long-term without having to change anything in your code.
Textbender is a system of collaborative writing based on recombinant text. It implements a social Web medium with potential applications ranging from open art to open democracy.
Turn traffic into pipeline and prospects into customers
For account executives and sales engineers looking for a solution to manage their insights and sales data
Docket is an AI-powered sales enablement platform designed to unify go-to-market (GTM) data through its proprietary Sales Knowledge Lake™ and activate it with intelligent AI agents. The platform helps marketing teams increase pipeline generation by 15% by engaging website visitors in human-like conversations and qualifying leads. For sales teams, Docket improves seller efficiency by 33% by providing instant product knowledge, retrieving collateral, and creating personalized documents. Built for GTM teams, Docket integrates with over 100 tools across the revenue tech stack and offers enterprise-grade security with SOC 2 Type II, GDPR, and ISO 27001 compliance. Customers report improved win rates, shorter sales cycles, and dramatically reduced response times. Docket’s scalable, accurate, and fast AI agents deliver reliable answers with confidence scores, empowering teams to close deals faster.
Babeldoc is integration tool that can plumb together data flows. It is completely configurable and scriptable. It is heavily XML biased but not exclusively so.
Auvai is a Java API and Java Swing based application for Text to Speech conversion of Unicode Tamil. Future direction of this API and application is to support Text to Speech conversion for all "Indic" languages.
The objective of the OpenBerg Project is to develop Open-Source, Open-Standards-based, Multi-Platform tools for eBook authors, editors and users. We are currently working on OpenBerg Lector, an e-Book reader, and OpenBerg Rector, an e-Book compiler.
The application is a text converter (RTF to PDF). The user can select a source .rtf file and then choose a destination file(.pdf). The RTF file is converted to PDF file. Based on vPDF @ http://sourceforge.net/projects/vpdf but supports text alignment.
ThiefscriptSE - The ultimate NukeZone thiefscript. Helps you pick the right thief target in the online game 'NukeZone'. Written in java to ensure cross-platform compatibility.
LiMa means Lightweight Markup Language. It is a parser for an easy to use ASCII/Text-based markup - comparable to Markdown or the Wikipedia-Markup language with special configurable extensions in defining Links and image-resources.
The Newswriter is a simple script to publish and administrate your News.
There is no need for a database. The News a stored in a simple file.
I've coded this script because the others I found were to complicated and
not adaptable enough.
KindEditor is a general-purpose online WYSWYG(What You See What You Get) HTML Editor. that is webbased and works in Mozilla, Firefox, Opera, Netscape, Internet Explorer.
CPLed is an OpenSIPS tool for editing CPL scripts in a friendly and easy graphical way. It can be used as a standalone application or embedded in a web page as applet. It also provide CPL script transport functionalities via SIP and HTTP protocols.
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.
Visual xsltproc is a tool which help to write xslt file, and debug it to find errors. It writes xml, and generates xml (Syntax highlighting of XML & line Nr.). Finally if the result is XSL-FO it generates the pdf on Apache FOP java. Build on QT4.2.
WordnetFlash will be a Flash interface to the very popular University of Princeton Wordnet project. Initial project will be based on Wordnet 2.0 layout, with the completion of testing, integration of Wordnet 2.1 will occur
This is a small command-line program to split a phone bill into several seperate ones to categorise the calls (e.g. for illustration which family member phones how much). It generates HTML files and is able to send them to specified email adresses.