AI Agents & Automation

Centific helps model labs and enterprises build, train, deploy, and govern intelligent systems by providing high-quality data, human expertise, and end-to-end platforms. The company focuses on generating, refining, and operationalizing real-world signals across language, vision, behavior, and expertise to enable AI systems to learn faster and perform better in production. Centific offers solutions for RL Environments-as-a-Service, Translation & Localization, Multilingual AI, Data Collection & Creation, RLHF & Preference Optimization, Supervised Fine Tuning, Model Safety & Evaluation, and Internationalization. Their platforms include Data Marketplace, Data Canvas, AI Data Foundry, and OneForma, designed to support continuous data loops for production AI.

QuickFiling is an AI-powered platform designed to simplify the complex process of drafting immigration petitions, including NIW, EB-1A, and O-1 cases. It provides an intelligent workspace that guides users step-by-step through agentic workflows, ensuring critical requirements are met. The platform features automated evidence analysis, AI-powered organization of hundreds of exhibits, and AI-assisted petition letter generation with smart suggestions and auto-citations. QuickFiling guarantees USCIS-ready documents, with AI-generated, compliant structures converted to LaTeX for publication-quality formatting. It also supports real-time collaboration and is trusted by petitioners and businesses globally, significantly reducing drafting time from months to hours.

Polyloop is the first AI-driven operating system designed specifically for non-profits, government, and funding ecosystems. It aims to declutter the challenges of evaluating outcomes by providing an evaluation co-pilot. The platform helps users plan their impact by building plans and generating outcomes with AI, reducing planning time from 60 hours to 6 minutes. It automates operational data collection and end-to-end benefits capture, offering multi-source automation. Polyloop also provides exceptional real-time reporting and evidence-based decision-making with analytics, and facilitates learning and case studies that are easily exportable, indexed, and searchable for future reference. This leads to significant improvements like 5% budget savings, 30% increase in KPI performance, and 7x increase in productivity.

Ionio specializes in transforming mid-market Retail & Ecom SaaS platforms (5M-100M ARR) into AI-native category leaders. They achieve this by building strategic AI features that deliver immediate ROI for merchants, enabling platforms to justify premium pricing and increase LTV. Their services include AI Wedge Discovery to identify unique features, full transformation from discovery to shipped product in one quarter, and ongoing AI Evolution Partnerships. Ionio offers Lighthouse Components like Prescriptive Intelligence, MicroSegments, Retail Embedding Classifier, Smart Product Bundling, and Visual Search Pipeline. They have a proven track record with over 35 projects delivered, helping clients defend against AI startups, monetize audiences with SaaS assets, and automate manual workflows.

Lawgic AI is an innovative legal technology solution designed to drive efficiency and innovation within the legal industry. It provides advanced AI-driven tools to help legal professionals and organizations navigate the complexities of a fast-paced environment. By leveraging artificial intelligence, Lawgic AI aims to streamline various legal processes, from document review to compliance management, ultimately enhancing overall operational efficiency. The platform is built to address the specific challenges faced by legal practitioners, offering solutions that can adapt to evolving legal landscapes and improve decision-making.

OdysseyGPT is an enterprise document intelligence and IDP platform designed to turn unstructured documents into reliable, citation-backed knowledge and structured data. It leverages retrieval-augmented generation, semantic search, and multi-step reasoning to extract data from various document types like contracts, invoices, resumes, and emails. The platform ensures data quality, transparency, and control by linking every extracted data point back to its exact source within the document. OdysseyGPT allows users to set up workspaces, roles, and approval steps, logging every action for auditability. It integrates with existing business systems like accounting, HR, CRM, and support tools, enabling seamless data flow while preserving source context. The tool is built with robust security features, including SSO, role-based access control, end-to-end encryption, and full audit trails.

Contractify is an intelligent contract management software that leverages AI to streamline the entire contract lifecycle. It helps organizations centralize, sign, and manage contracts efficiently, ensuring compliance and reducing risks. Key features include the AI Contract Analyst ADA for errorlessly analyzing and digitizing contracts, a dynamic contract library for organized storage, and automated alerts to prevent missed deadlines. The platform also offers approval and signing flows, reporting dashboards, and user privileges for comprehensive control. Contractify aims to save time, improve collaboration, and provide a proactive overview of all contractual obligations, making it suitable for legal, finance, management, and purchasing teams.

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.

gmft is an open-source tool designed for efficient and accurate table extraction from PDF documents. It stands out for its lightweight architecture, modularity, and high performance, making it a reliable choice for processing large volumes of PDFs. The tool leverages Microsoft's Table Transformers, known for their qualitative performance, to convert tables into multiple formats including Pandas dataframes, markdown, LaTeX, HTML, CSV, JSON, lists of text with positions, and cropped images. It operates on CPU, eliminating the need for a GPU, and boasts significantly faster processing speeds compared to alternatives. gmft focuses solely on table extraction, providing excellent quality even with complex table structures like multi-column headers and spanning cells, making it ideal for scientific papers and structured data retrieval.

協助專業人士和學習者快速處理海量資料與資訊並利用適當AI工具的小助手 is a small AI assistant designed to help professionals and learners efficiently manage large amounts of data and information by leveraging appropriate AI tools. This Chrome extension facilitates quick copy and paste functionality, automatically including the source URL when highlighting text with the mouse. It also supports standard keyboard shortcuts (Ctrl+C and Ctrl+V) for pasting both text and screenshots. A key feature is the ability to set special tags like "Keyword" and "To check" within drafts, allowing users to add comments for annotation. This streamlines subsequent organization and verification processes, making it an invaluable tool for research, data compilation, and document preparation.

LayoutParser is a comprehensive toolkit designed to streamline Deep Learning Based Document Image Analysis (DIA) tasks. It offers a rich repository of deep learning models for layout detection, along with unified APIs for easy integration and use. The toolkit includes carefully designed layout data structures optimized for DIA, enabling tasks like selecting specific layout elements or performing OCR on detected regions. LayoutParser also provides flexible APIs for visualizing detected layouts and supports loading layout data from various formats including JSON, CSV, and PDFs. It functions as an open platform, encouraging the sharing of layout detection models and DIA pipelines within the community, making it a versatile resource for researchers and developers in the field.

ImageToText.info is a free online OCR tool designed to accurately extract text from various image formats, including JPG, PNG, GIF, and PDF. Leveraging advanced AI technology, specifically tesseract-ocr, it offers high accuracy in converting visual text into editable digital formats. Users can upload, drag-and-drop, or paste image URLs to quickly convert single or batch images. The tool supports over 20 languages, allowing for diverse text extraction needs. Extracted text can be downloaded as a text file or copied to the clipboard, making it convenient for editing or integration into other documents. ImageToText.info emphasizes user privacy, stating no data is transmitted or stored, and offers a simple, registration-free experience for quick text extraction.

obsidian-text-extractor is an Obsidian plugin designed to extract text from images, PDFs, and office documents using OCR technology. It acts as a "companion" plugin, primarily useful when integrated with other Obsidian plugins like Omnisearch, but can also be used independently for quick text extraction. The plugin supports various image formats, PDFs, and office documents (.docx, .xlsx). It processes text locally but requires an internet connection to download language files for the underlying Tesseract OCR library. Extracted texts are cached as local JSON files, which can be synced across devices, allowing mobile users to access cached texts even though direct extraction doesn't work on mobile.

PDF Summarizer is an AI-powered tool designed to streamline document analysis by summarizing long PDFs. Users can upload documents and engage in multi-file chats, allowing them to ask questions across multiple documents simultaneously, which is ideal for research projects. The system provides detailed or short summaries, extracts key points, and can even create notes, flashcards, and quizzes. A standout feature is its ability to translate any PDF into a preferred language instantly. The tool also offers a side-by-side view, linking questions directly to specific parts of the PDF for easy source checking and deeper exploration without losing context. It supports PDF files up to 50MB and 500 pages, ensuring data security with SOC2 Type II certification.

Towhee Examples offers a diverse collection of applications designed to analyze unstructured data using the Towhee framework. These examples cover a wide range of tasks, such as reverse image search, reverse video search, audio classification, and question and answer systems. Additionally, it includes applications for molecular search and deepfake detection. The platform aims to democratize the process of generating embedding vectors (x2vec) by providing easily runnable examples that leverage machine learning models and operations. It supports various models like ResNet, VGG, EfficientNet, ViT for image tasks, DPR for NLP, and Pytorchvideo for video. This resource is ideal for developers and data scientists looking to implement advanced data analysis solutions.

RAGHub serves as a comprehensive, community-driven directory for the rapidly expanding field of Retrieval-Augmented Generation (RAG). It curates a living collection of new and emerging RAG frameworks, projects, and resources, addressing the challenge of keeping up with the constant influx of new tools. The platform aims to help users navigate the RAG ecosystem, providing a centralized place to discover innovations and assess the relevance of various tools. RAGHub categorizes resources into RAG Frameworks, Evaluation and Optimization Frameworks, Engines, Data Preparation Frameworks, Projects, and general Resources. It encourages community contributions, allowing users to add new tools and insights, fostering a collaborative environment for RAG development.

RepoToTextForLLMs is a Python script designed to automate the analysis of GitHub repositories, specifically tailored for use with large context LLMs. It efficiently fetches README files, maps out the repository's structure through an iterative traversal method, and extracts the content of non-binary files. The tool intelligently skips binary files to streamline the analysis process. A key feature is its ability to provide structured outputs complete with pre-formatted prompts, aiding in the comprehensive evaluation of the repository's content by LLMs. Users need Python, the `PyGithub` package, and a GitHub Personal Access Token configured as an environment variable to get started.

SQLite-Vector is a cross-platform, ultra-efficient SQLite extension designed to integrate vector search directly into embedded databases. It operates seamlessly across iOS, Android, Windows, Linux, and macOS, utilizing minimal memory (defaulting to just 30MB). This tool eliminates the need for complex preindexing, allowing for immediate vector search on existing data stored as BLOBs in ordinary SQLite tables. It supports various vector types including Float32, Float16, BFloat16, Int8, UInt8, and 1Bit, alongside highly optimized distance functions like L2, Cosine, and Dot Product. SQLite-Vector is ideal for Edge AI applications, enabling offline, privacy-preserving AI workloads with real-time performance directly on devices.

WebGLM is an efficient web-enhanced question-answering system developed by THUDM, presented at KDD 2023. It leverages a 10-billion-parameter General Language Model (GLM) to integrate web search and retrieval capabilities, significantly improving the accuracy and relevance of answers. The system features an LLM-augmented Retriever for enhanced web content retrieval, a Bootstrapped Generator for human-like response generation, and a Human Preference-aware Scorer to ensure useful and engaging content. WebGLM supports both 2B and 10B parameter models and offers options for searching via SerpAPI or Bing. It is designed for researchers and developers looking to implement advanced, web-aware QA systems.

vqa.pytorch is an open-source project offering a PyTorch implementation for Visual Question Answering (VQA). Developed by researchers at LIP6 and Heuritech, this tool aims to facilitate the reproduction of state-of-the-art results, particularly those achieved with the MUTAN: Multimodal Tucker Fusion for VQA method on the VQA 1.0 dataset. It provides a modular and efficient codebase for further research on various VQA datasets. Key features include support for different VQA datasets (VQA 1.0, VQA 2.0, VisualGenome), pretrained models, and tools for extracting features from images using convolutional neural networks. The repository also includes documentation on its architecture, options, and quick examples for training and evaluating models, making it a valuable resource for researchers and students in the field of computer vision and natural language processing.

mPLUG-DocOwl is a powerful open-source modularized multimodal large language model designed for comprehensive document understanding. It excels in OCR-free document analysis, enabling the extraction of information from various document types without relying on traditional optical character recognition. The tool provides training code for finetuning stronger models with custom datasets, making it highly adaptable for specific research or application needs. It supports multiple versions like DocOwl1.5 and DocOwl2, with capabilities extending to chart understanding (TinyChart) and scientific diagram analysis (PaperOwl). Demos are available on HuggingFace and ModelScope, showcasing its capabilities in tasks like DocVQA, InfoVQA, and ChartQA.

Lawgmented is a desktop application designed for AI-powered contract review, seamlessly integrating with Microsoft Word. It allows users to open documents, select their party and role, and then run a review that highlights critical clauses and explains potential risks in plain language. The tool offers one-click redrafting of clauses, generating improved language tailored to the user's side of the deal, which can be inserted directly into Word with Track Changes. Additionally, Lawgmented can draft new clauses aligned with the contract's existing defined terms and style. It aims to simplify the contract review process, making it accessible for anyone while providing powerful features for legal professionals.

Polymath is an applied research lab dedicated to advancing the reliability and autonomy of AI agents. The company specializes in creating highly advanced simulation environments that accurately reflect real-world conditions. These environments are crucial for training and evaluating AI agents, enabling them to practice and learn through experience, ultimately performing useful work over long horizons with minimal human supervision. Polymath partners with leading model labs to push the boundaries of agent capabilities and is backed by prominent investors like Base10 and Y Combinator. Their work is vital for developing safe and highly capable AI systems, addressing some of the most important challenges in agent autonomy.

anago is a Python library designed for sequence labeling tasks, including Named Entity Recognition (NER) and Part-of-Speech (PoS) Tagging. Built with Keras, it leverages advanced models like Bidirectional LSTM-CRF and ELMo to achieve high performance. A key differentiator is its independence from language-dependent features, making it easily adaptable for various languages. The library offers essential methods for model training, evaluation, and text tagging, along with support for custom models, pre-trained model downloads, and GPU acceleration. It's particularly useful for researchers and developers working on natural language processing applications.