Data & Analytics

LlamaGym is an open-source framework designed to simplify the fine-tuning of Large Language Model (LLM) agents using online reinforcement learning. Unlike many current LLM-based agents that do not learn continuously in real-time, LlamaGym enables agents to interact with an environment and receive immediate reward signals for ongoing learning. It addresses common challenges such as managing LLM conversation context, handling episode batches, assigning rewards, and setting up Proximal Policy Optimization (PPO). By providing a single abstract Agent class, LlamaGym allows developers to quickly iterate and experiment with agent prompting and hyperparameters across various Gym environments, making the process of integrating LLMs with RL more accessible. While currently a work in progress, it aims to streamline the development of adaptive LLM agents.

Maxun is an open-source, no-code web data platform designed to transform websites into structured, reliable data. It supports various functionalities including extraction, crawling, scraping, and search, and is built to scale from simple tasks to complex, automated workflows. Key features include a Recorder Mode to turn browsing actions into reusable extraction robots, and an AI Mode that uses natural language for LLM-powered extraction. Maxun can convert full webpages into clean Markdown or HTML, capture screenshots, and crawl entire websites with control over scope. It also facilitates automated web searches with time-based filters and offers a comprehensive developer SDK and CLI for programmatic control and data automation. The platform is self-hostable, provides RESTful endpoints, and integrates with various tools, making it suitable for lead generation, market research, and content aggregation.

Closely is an AI-driven outbound platform designed to automate LinkedIn and email outreach. It combines real-time data enrichment, intelligent sales agents, and multichannel campaigns to deliver personalized messages that get replies. The tool offers safe LinkedIn automation that mimics real human behavior, including smart limits and delays, to ensure account safety while increasing reply rates. Users can build LinkedIn outreach sequences, integrate them with email steps, and track comprehensive analytics across campaigns and teams. Closely also features a unified inbox for managing LinkedIn DMs, InMails, and email replies, along with a LinkedIn email and phone number finder for enriching contact data. It integrates deeply with CRMs like HubSpot, Salesforce, and Pipedrive to keep sales data clean and synchronized.

Ripcord is an advanced platform that leverages proprietary robotics, artificial intelligence, and machine learning to convert various types of documents into actionable data. It specializes in digitizing paper documents into high-quality digital files while maintaining integrity, and then uses AI to classify, extract, validate, and enrich the trapped data. This process enables organizations to automate key processes, access critical information, and unlock new opportunities. Ripcord supports both structured and unstructured, static and in-motion documents, making data easy to access and ready for use, either through existing tools or its cloud-based content platform, Canopy.

Scrapecraft is an AI-powered web scraping editor designed to simplify the creation and management of web scraping pipelines. It offers a visual workflow builder, allowing users to intuitively design their scraping processes. Leveraging AI assistance, similar to tools like Cursor but specialized for web scraping, Scrapecraft enables users to build, test, and deploy scrapers using natural language prompts. Key features include support for multi-URL bulk scraping, dynamic schema definition with Pydantic, and Python code generation with async capabilities. The platform also provides real-time WebSocket streaming for data and offers results visualization in table and JSON formats. Built with a robust tech stack including FastAPI, LangGraph, ScrapeGraphAI, React, and PostgreSQL, Scrapecraft also supports auto-updating deployments via Watchtower, ensuring continuous operation without manual intervention.

Fama Technologies Inc. offers an AI-powered solution for social media screening, helping organizations identify workplace-relevant risks before and during employment. The tool compliantly searches over 10,000 online public sources and top social media sites like TikTok, X (Twitter), Facebook, and Instagram to detect misconduct signals such as harassment, hate speech, and threats of violence. Fama's behavior-first AI identifies 8 types of misconduct in over 30 languages, while ensuring compliance with EEOC, FCRA, GDPR, and PIPEDA standards by removing protected class information. It offers both pre-employment and ongoing employee screening, providing fast, reliable insights within 24-48 business hours. Fama integrates with various HR Tech systems and is trusted by global employers to improve quality of hire and avoid risk.

File AI is an AI-native data preparation and automation platform designed to unify data capture, governance, and orchestration into auditable AI workflows. It transforms unstructured data into trusted intelligence across various enterprise functions. The platform features fileForge, an AI-native data intelligence engine, alongside purpose-built solutions like fileLedger for financial operations automation and fileShield for intelligent case management in regulated environments. Key capabilities include multimodal AI OCR, classification, schema extraction, SOP-driven workflow engines, and over 100 ERP and system integrations. File AI aims to build the foundation for agentic AI at scale, providing the context, validation, and control needed for AI agents to act with confidence in real enterprise workflows.

Show Facebook Computer Vision Tags is a simple browser extension for Chrome and Firefox designed to make users aware of the automated image tagging performed by Facebook's Deep ConvNet. Since April 2016, Facebook has been adding alt tags to uploaded images, populated with keywords describing their content. This extension overlays these generated tags directly onto photos in your Facebook timeline, allowing you to see what objects, activities, locations, and events Facebook's AI identifies. While these tags improve accessibility for blind users, the extension's primary goal is to highlight the extensive data extraction capabilities of major internet companies from user photographs, prompting users to consider their digital privacy. It's a straightforward tool for anyone curious about the information Facebook gleans from their visual content.

Table Transformer (TATR) is a deep learning model developed by Microsoft for extracting tables from unstructured documents, including PDFs and images. Based on object detection, TATR can be trained to work across various document domains, with pre-trained model weights available for the PubTables-1M dataset. The repository also provides the official code for the PubTables-1M dataset, a large-scale dataset for table detection, structure recognition, and functional analysis, and the GriTS evaluation metric for table structure recognition. Researchers and developers can use TATR to detect and recognize tables, convert them to HTML or CSV, and train custom models for specific needs.

SmartProxy is a leading global residential proxy service provider, offering access to over 100 million residential IPs across 200 countries. Engineered for reliable web data collection and AI workflows, it provides blazing-fast, enterprise-grade access to a vast network of IPs. The platform supports various proxy types including Residential Proxy, Unlimited Proxy, Static Residential Proxy, Static Data Center Proxy, and Long Acting ISP Proxy, catering to diverse business needs. SmartProxy also offers Web Scraper APIs for real-time structured data extraction and customized solutions. With features like free geolocation, real residential IPs, and no hidden fees, it ensures high success rates for scraping and automation. The service is optimized for AI/LLM data pipelines, offering stable and reliable connections for AI data operations, ad verification, price monitoring, social media management, e-commerce, and market research.

Talk2Page is an AI-powered webpage analysis tool designed to enhance your browsing experience by turning any webpage into an interactive knowledge session. With its Chrome extension, users can ask questions about webpage content and receive instant, contextual answers powered by AI. The tool features an intuitive interface, smart content extraction that removes unnecessary elements for clean text, and seamless OpenAI integration. It simplifies the process of extracting, processing, and understanding web content, making it ideal for anyone looking to quickly gain insights from online articles, documents, or other web resources.

ProntoHQ is a comprehensive B2B prospecting platform designed to significantly boost lead generation and sales outreach efficiency. It enables users to build high-converting outreach lists in seconds by finding companies, leads, emails, and phones through over 100 data providers. Key features include finding leads based on persona, waterfall enrichment for higher data accuracy, and real-time tracking of job changes and new hires to identify optimal outreach moments. The platform also offers AI-powered lead qualification and cleaning, integration with popular CRM and outreach tools, and robust data verification processes to ensure high accuracy of contact information. ProntoHQ aims to reduce the time spent on manual list building and improve conversion rates for sales and growth teams.

Website Cloner is a powerful tool designed to replicate the front-end design, structure, and functionality of any website. It leverages HTTP crawling and asset mapping to create accurate duplicates, which can then be hosted, modified, and rebranded. The tool is ideal for developers, businesses, and marketing teams looking to accelerate website deployment, create backups, test new features, or analyze competitor sites. It emphasizes legal and ethical cloning practices, providing guidance on how to use cloned sites responsibly for purposes like redesigns, migrations, and educational analysis. Advanced features include AI-assisted cloning for generating editable code and integration with modern web development workflows like Jamstack.

ocrbase is a lightweight, model-agnostic OCR API designed for standardizing document parsing across various visual language models (VLMs). It allows users to convert PDF and image documents into structured data formats such as Markdown and JSON. The tool is self-hostable and integrates with leading OCR models like PaddleOCR and GLMOCR, which boast high accuracy on benchmarks. Key features include API endpoints for parsing documents, asynchronous job processing, and structured data extraction. It also offers optional S3 input staging and BullMQ parse queuing for enhanced scalability and reliability, making it suitable for developers needing robust document processing capabilities.

Parsera is a lightweight Python library designed for efficient web scraping using Large Language Models (LLMs). It provides a straightforward interface, allowing developers to easily extract structured data from websites. Users can define the elements they wish to scrape, such as titles, points, or comments, and Parsera will return the data in a JSON format. The library supports both synchronous and asynchronous operations, and can be run via pip installation, Jupyter Notebook, CLI, or Docker. It also offers flexibility to integrate custom LLM models and playwright scripts, making it a versatile tool for data extraction tasks.

Qmedia is an open-source multimedia AI content search engine specifically designed for content creators. It provides rich information extraction methods for text, images, and short video content, integrating unstructured data to build a multimodal RAG content Q&A system. Key features include content cards for displaying extracted information, efficient analysis of various media types, and the ability to generate customized search results. Qmedia supports full local deployment of its web app, RAG server, and LLM server, enabling offline content search and Q&A for private data. It also offers multi-modal RAG content Q&A and supports Google content search.

Scylla is an intelligent, open-source proxy pool specifically engineered for efficient web content extraction. This tool is primarily designed to assist in gathering vast amounts of data from the internet, which is crucial for the development and training of large language models (LLMs). By providing a robust and flexible proxy solution, Scylla helps automate the complex process of collecting online information, making it an invaluable asset for AI researchers and developers. Its open-source nature fosters community collaboration and allows for customization to suit specific data extraction needs, ensuring adaptability and continuous improvement in the evolving landscape of AI development.

Twitter-Insight-LLM is an open-source project designed for comprehensive Twitter data management and analysis. It facilitates fetching liked tweets using Selenium, saving this data into structured JSON and Excel files for easy access. Beyond basic data ingestion, the tool supports initial data analysis, allowing users to gain insights from their collected Twitter data. A standout feature is its experimental embedding-based image search, which enables natural language queries for unlabeled images without requiring GPU support. This functionality supports multiple languages, enhancing its utility for diverse users. The project also integrates with OpenAI API for image captioning, providing a robust solution for understanding and organizing visual content from Twitter.

NO (DataPlus) is a crowdsourcing platform specifically designed for AI data collection. It features a unique guild management system that streamlines team collaboration, making it efficient for collecting and annotating various types of data, including audio, video, and images. The platform's primary focus is to provide high-quality, diverse datasets essential for training and developing artificial intelligence models. By facilitating organized data collection and annotation processes, NO (DataPlus) aims to support AI researchers, developers, and businesses in building robust and accurate AI applications.

ExtractNinja is a data extraction tool designed to automate the gathering of information from various websites and online sources. It aims to streamline the data collection process for users involved in research, analysis, and business intelligence. The tool focuses on providing an efficient way to acquire structured data, which can then be utilized for various strategic and operational needs. By automating the extraction process, ExtractNinja helps users save time and resources that would otherwise be spent on manual data collection. Its capabilities are geared towards supporting informed decision-making through readily available and organized data.

GMapsScraper AI is a free online Google Maps scraper designed to efficiently collect business data for lead generation. Unlike traditional tools requiring plugin installations, GMaps Scraper operates entirely online, extracting contact information instantly. Users can enter search keywords and locations, and the tool automatically gathers business names, phone numbers, addresses, emails, websites, and ratings. This data is then compiled into a clean, organized spreadsheet ready for CRM or email campaigns. Key features include bulk extraction, smart filtering by rating or price level, and multi-location targeting. It extracts publicly available information from Google Maps, ensuring compliance with data protection regulations and offering secure, browser-based technology. GMaps Scraper aims to save hours on manual data collection, providing verified business data for successful outreach.

Galadon offers a suite of free-to-try sales prospecting tools designed for B2B outbound sales teams, founders, and agencies. Users can find verified email addresses, check email validity to reduce bounces, and locate direct mobile numbers from emails or LinkedIn profiles. Beyond contact data, Galadon provides tools for property searches, revealing owner names, phone numbers, and address history for US properties. It also facilitates criminal records searches and AI-powered background checks for people and companies, assessing trust scores and identifying red flags. The platform includes a B2B Company Finder for generating targeting criteria and a Tech Stack Scraper to identify technologies used by websites. Galadon is powered by ScraperCity, which offers bulk processing and API access for scaled operations.

Quickcode.ai offers an AI-powered platform designed to simplify trade compliance for manufacturers, importers, and trade compliance professionals. The tool provides real-time visibility into tariff changes, product codes, and regulatory risks, helping users detect misclassified products and stay updated on tariffs, Partner Government Agencies (PGAs), and Antidumping/Countervailing cases. Users can import product catalogs for free compliance audits, classify products with explainable AI, and access global HS codes for over 160 countries. Quickcode integrates legal sources like HTS Schedule, CROSS Rulings, and WCO Notes into a single pane, significantly reducing the time and effort required for compliance workflows. It also offers 24/7 compliance monitoring to automatically update data and alert users to necessary interventions.

imagetotext.cc is an online OCR platform designed to quickly and accurately extract text from various image formats, scanned documents, handwritten notes, and screenshots. It leverages advanced OCR technology to convert images into editable text, supporting formats like JPG, PNG, WEBP, GIF, BMP, HEIC, PDF, and TIFF. Key features include the ability to extract text from blurry images, detect mathematical syntax, and support multiple languages. The tool offers batch processing, allowing free users to convert up to 5 images and premium users up to 50 images at once, enhancing productivity for tasks like document digitization, data entry automation, and content analysis.