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
Smart Business Texting that Generates Pipeline
Create and convert pipeline at scale through industry leading SMS campaigns, automation, and conversation management.
TextUs is the leading text messaging service provider for businesses that want to engage in real-time conversations with customers, leads, employees and candidates. Text messaging is one of the most engaging ways to communicate with customers, candidates, employees and leads. 1:1, two-way messaging encourages response and engagement. Text messages help teams get 10x the response rate over phone and email. Business text messaging has become a more viable form of communication than traditional mediums. The TextUs user experience is intentionally designed to resemble the familiar SMS inbox, allowing users to easily manage contacts, conversations, and campaigns. Work right from your desktop with the TextUs web app or use the Chrome extension alongside your ATS or CRM. Leverage the mobile app for on-the-go sending and responding.
Cross-platform command-line tool for creation of PDF documents from scans/photos of pages in JPEG (.jpg) format and the lightest weight ANSI C library to put multiple JPEG files into one PDF file.
You can add handwritten comments to PDF scans (over original images) with xournal: http://xournal.sourceforge.net/
It supports graphics tablets and saves comments to PDFs as vector data.
Books Organizer, an organizer for pdf files based on sqlite and with a built-in reader. Bring your favorite PDF pages all in one! Make your own extract pages from existing ones
Xena transforms files into open data formats for long-term digital preservation, encodes content in Base64 and wraps in XML metadata. Formats supported include MBOX, PST, MSG, DOC, XLS, PPT, RTF, PNG, XML, PDF, JPG, TIFF, PCX, WAV, MP3 and more.
NO LONGER MAINTAINED, NO LONGER SUPPORTED
An opensource typesetting environment for editing and publishing Carnatic music books in Indian languages. Supports Phonetic Translation of notation & lyrics and uses CFugue Runtime to automatically generate MIDI song files from the music notation.
Secure and customizable compute service that lets you create and run virtual machines.
Computing infrastructure in predefined or custom machine sizes to accelerate your cloud transformation. General purpose (E2, N1, N2, N2D) machines provide a good balance of price and performance. Compute optimized (C2) machines offer high-end vCPU performance for compute-intensive workloads. Memory optimized (M2) machines offer the highest memory and are great for in-memory databases. Accelerator optimized (A2) machines are based on the A100 GPU, for very demanding applications.
“Saaghar” (ساغر) is a Persian poetry software written by C++ under Qt framework, it uses "ganjoor" database as its database. It has tab feature in both its “Viewer” and its “Search” page that cause it be suitable for research goals.
KAPDF 1.0 was released.KAPDF is a Free Libre Open Source PHP class for generating PDF documents without requiring external extensions.KAPDF Supports UTF-8, Unicode, RTL languages and (x)HTML. For more information visit http://www.kukaka.org
An image postprocessor for the DIY Book Scanner described on instructables.com and diybookscanner.org. Gets images ready for OCR or for PDF. Written in Java based on a partial port of the Leptonica image processing library.