AI Agents & Automation

qdrant-client is a Python client library designed for seamless interaction with the Qdrant vector search engine. It offers comprehensive type definitions for all Qdrant API methods, facilitating both synchronous and asynchronous requests. The library supports a local mode for development, prototyping, and testing without requiring a running Qdrant server, and can easily switch to server mode for scaling. Key features include REST and gRPC support, minimal dependencies, and extensive test coverage. Additionally, it provides an Inference API for creating embeddings locally with FastEmbed or remotely with Qdrant Cloud models, simplifying the process of generating and uploading vectors.

LegalLens is an AI-powered educational tool designed to assist students in analyzing and understanding legal documents. It provides AI-powered summaries and extracts key points from legal texts, making complex legal information more accessible. The tool is specifically developed for educational purposes, helping students learn and comprehend legal materials more efficiently. By breaking down lengthy documents into digestible summaries and highlighting essential information, LegalLens aims to enhance the learning experience for those studying law.

Rag-chatbot is an open-source tool designed for local interaction with multiple PDF documents, enabling users to chat and retrieve information from their files. It supports a variety of models from Hugging Face and Ollama, providing flexibility in AI backend choices. The tool can be easily set up and run either locally or on Kaggle, making it accessible for different user environments. Its key features include processing multiple PDF inputs, a simple user interface built with Gradio, and upcoming support for multiple languages. This makes it a versatile solution for anyone needing to query and extract insights from a collection of PDF documents without relying on cloud services.

TextTeaser is an open-source project providing an automatic summarization algorithm. It leverages both natural language processing (NLP) and machine learning techniques to generate effective and concise summaries from text documents. The tool is primarily implemented in Python, making it accessible for developers and researchers familiar with the language. To set up and run TextTeaser, users need to have SBT (Scala Build Tool) installed, as the project also utilizes Scala. This combination allows for a robust approach to text summarization, offering a foundation for integrating summarization capabilities into various applications or for academic research.

Axal is an AI-native platform designed to automate critical business processes for distributors and manufacturers. It deploys AI workers that connect directly to your ERP system (including SAP, Oracle, Epicor, and Infor) to handle tasks across front office (sales) and back office (finance) functions. Key capabilities include automating order entry by reading inbound POs from email, generating quotes in seconds, and providing real-time pricing and availability for inside sales. For back-office operations, Axal automates accounts payable invoice-PO matching, purchasing updates, accounts receivable cash collection, and email inquiry handling. The platform aims to significantly reduce manual work, improve accuracy, and free up teams to focus on higher-value activities, with rapid deployment and impact in days.

Goddard - Discovery offers an intelligent research assistant called Inventia AI, designed to empower researchers by augmenting their capabilities. This platform helps users find and organize research articles, discover latent knowledge within their field, and identify collaboration opportunities. Beyond Inventia AI, Goddard - Discovery also provides services in Artificial Intelligence, Data Science, and Web & App Development. The team is committed to advancing research communities by integrating AI into research processes, enabling breakthroughs and elevating work to unprecedented levels. They are actively shaping the future of research by providing tools and services that enhance scientific investigation across diverse domains.

CrushBank is an AI-powered platform designed to transform IT operations for Managed Service Providers (MSPs) and enterprise help desks. It leverages a managed data lakehouse to mine data, refine analytics, and power intelligent AI agents and automations. The platform enables organizations to build smarter automations using their own trusted data and machine learning, achieving over 90% accuracy in ticket classification, budgeting, and prioritization. CrushBank's autonomous AI agents continuously analyze ticket data to identify reopened tickets, uncover trends, and accelerate resolution times. It integrates with existing Professional Services Automation (PSA) systems, turning them into AI-powered engines with automations, document and conversational search, internet search, insights, and document creation. Additionally, its SmartShift and SmartArchive features facilitate seamless PSA data migration and intelligent archiving of legacy systems.

document.ai offers a universal local knowledge base solution built upon vector databases and GPT-3.5. It enables users to transform their local answer datasets into vector embeddings, which are then stored in a vector database. When a user inputs a query, the system converts the question into a vector, retrieves the most similar answers from the database, and then uses GPT-3.5 to optimize the overall structure and coherence of the response. This approach is particularly beneficial for chat-based scenarios like customer service, where a more natural and contextually relevant reply is desired. The project also explores advanced techniques for data optimization, such as addressing inaccurate query data, leveraging self-trained embedding models, and considering fine-tuning GPT models for specialized domains.

law-cn-ai is an open-source AI legal assistant designed to streamline legal research and document processing. It utilizes AI to pre-process legal knowledge bases from sources like LawRefBook/Laws, storing embedded vectors in PostgreSQL using pgvector for efficient similarity searches. Key features include an intelligent writing assistant, an AI encyclopedia, a prompt generator, and AI translation capabilities. The tool is built on a Next.js application, integrating with OpenAI for text completion and Vercel for deployment, making it a powerful resource for legal professionals seeking to enhance productivity and accuracy in their work.

HIA (Health Insights Agent) is an AI-powered tool designed to analyze blood reports and deliver comprehensive health insights. It utilizes an agent-based architecture, featuring an Analysis Agent for in-context learning and a built-in knowledge base, alongside a Chat Agent for RAG-powered follow-up Q&A. The system employs a multi-model cascade via Groq with automatic fallback for robust AI processing. Users can upload PDF reports (up to 20MB, 50 pages) or use a sample report, with daily analysis limits. It includes secure Supabase Auth, session validation, and history management, all presented through a modern, responsive Streamlit UI.

Graph-rag-agent is an open-source project focused on building explainable and inferential intelligent question-answering systems by combining GraphRAG and private Deep Search. It integrates various RAG technologies like GraphRAG, LightRAG, and Neo4j-llm-graph-builder for comprehensive knowledge graph construction and search capabilities. The tool features a multi-agent collaborative architecture, allowing different types of agents to work together for complex problem-solving. A key differentiator is its robust evaluation system, offering over 20 metrics to assess system performance. It also supports incremental updates for dynamic knowledge graph building and includes mechanisms for entity disambiguation and alignment to improve data quality. The project provides a full-stack solution with a backend service (FastAPI) and a frontend interface for interactive knowledge graph visualization and real-time streaming responses.

GVA NDA Check is an AI-powered service designed to simplify the review of Non-Disclosure Agreements (NDAs). Users can upload Word or PDF NDA documents, and the AI, trained with legal expertise, will analyze each clause. It visualizes potential risks in stages, extracts necessary corrections, and offers revision examples tailored to different stances, such as company-favorable or neutral. This allows users to easily modify contract clauses based on the provided insights. The service aims to make contract signing more accessible and secure for everyone, particularly beneficial for small to medium-sized businesses and startups without dedicated legal departments.

DocuSwift.in is an AI-powered legal platform specifically designed to enhance the efficiency and accuracy of legal professionals in India. It offers a comprehensive suite of AI tools for various aspects of legal practice, including research, analysis, drafting, and review. Key features like Case Search™ allow lawyers to ask natural language questions to instantly find relevant cases and receive smart case contexts. Case Chat™ enables instant interaction with lengthy legal documents for key insights and summaries, while Case Draft™ provides AI-powered enhancements for legal drafting, including smart citation insertion and instant counter-draft generation. The platform aims to be a one-stop solution for legal professionals, helping them focus on counsel rather than paperwork.

PaddleMIX is a comprehensive multi-modal large model development suite built on PaddlePaddle, designed to integrate and explore various modalities including image, text, and video. It covers a wide range of multi-modal tasks such as visual language pre-training, fine-tuning, text-to-image generation, text-to-video generation, and multi-modal understanding. The platform provides an out-of-the-box development experience while also allowing for flexible customization to meet diverse needs, aiding in the exploration of general artificial intelligence. Key features include a rich library of multi-modal models, a full-lifecycle development experience from data processing to deployment, and high-performance distributed training and inference capabilities.

PandaWiki is an open-source, AI large language model-driven system designed for building intelligent knowledge bases. It enables users to quickly create product documentation, technical documentation, FAQs, and blog systems. The platform leverages AI for content creation, question answering, and search functionalities, enhancing the efficiency and intelligence of knowledge management. Key features include robust rich-text editing compatible with Markdown and HTML, export options to Word, PDF, and Markdown, and easy integration with third-party applications like web widgets or chat bots for DingTalk, Feishu, and WeChat. PandaWiki also supports content import from various sources, including web URLs, sitemaps, RSS feeds, and offline files.

PDFTranslator is a free, AI-powered online tool designed to translate PDF documents quickly and accurately into over 100 languages. It stands out by preserving the original formatting, layouts, tables, images, and fonts in the translated file, ensuring a professional look without requiring edits. The tool supports OCR PDF translation for scanned documents, allowing text extraction and translation from images. It can handle long PDF documents up to 20MB per file, making it suitable for reports, contracts, and books. With a focus on security and privacy, files are processed via secure SSL and automatically deleted from servers within one hour. PDFTranslator offers unlimited translations without sign-up, credit cards, or hidden fees, making it an accessible solution for students and professionals alike.

RealtyGenius.AI is an AI-powered real estate assistant designed to streamline document management and collaboration for real estate professionals. Users can effortlessly upload and organize all their real estate documents in one secure place. The platform enables natural language interaction with documents, allowing users to chat with them as if they were human and get instant answers to their questions. It also facilitates seamless team collaboration, making it easy to share information and work together. With end-to-end encryption, RealtyGenius.AI ensures documents are secure at rest and in transit, providing a reliable solution for managing critical real estate information.

SimpleMem is an advanced memory framework designed for LLM agents, offering efficient lifelong memory capabilities for both text and multimodal data. It employs semantic lossless compression to store, compress, and retrieve long-term memories, ensuring high information density and token utilization. The system features a three-stage pipeline: Semantic Structured Compression, Online Semantic Synthesis, and Intent-Aware Retrieval Planning. Omni-SimpleMem extends these capabilities to include image, audio, and video, achieving state-of-the-art performance on benchmarks like LoCoMo and Mem-Gallery. It supports cross-session memory, allowing agents to recall context and learnings across conversations, and integrates with platforms like Claude, Cursor, and LM Studio via MCP or Python.

Chata.ai is an AI analytics platform designed for proactive insights, monitoring business data across various systems 24/7. It delivers real-time, hallucination-free insights and alerts to the right personnel before performance is impacted. The platform uses deterministic AI grounded in structured data, ensuring reliable answers without the need for SQL, dashboards, or a dedicated data team. It helps streamline data access across sources, automatically delivers reliable insights, and allows teams to ask natural-language questions to understand the reasons behind changes. Chata.ai is ISO 27001 and SOC 2 Type II certified, ensuring data protection and security.

AutoForm is an AI data entry agent designed to eliminate manual data entry by instantly converting unstructured files and web content into clean, structured data. It processes various inputs including PDFs, spreadsheets, emails, decks, and web pages, capturing every field and cleaning/labeling data using natural language. Users can then auto-fill forms, send results to other applications, or download the data in formats like Excel, CSV, or JSON. The tool offers features like AI-powered auto-fill, data refinement, and smart storage for processed documents. It also supports AI training for customized data outputs, bulk processing, and API access for enterprise automation, ensuring consistent and reliable results without coding.

ContractCrab is an AI-powered SaaS platform designed to streamline contract management by automating contract review and analysis. It helps users quickly identify potential risks, unfavorable clauses, and suggest improvements in various contract types. The platform utilizes natural language processing to understand contract content, extract key clauses, and shorten lengthy legal documents while maintaining accuracy. ContractCrab offers different plans, including a pay-as-you-go option and monthly subscriptions, making it accessible for individuals, small businesses, and enterprises. It supports multiple document formats like PDF, DOCX, and TXT, and prioritizes data security with end-to-end encryption and user data privacy.

Finden is an AI-powered workspace designed to connect, organize, and manage files and data across various digital locations, including drives, emails, messages, and applications. It enables users to search, chat, and research across all their personal and enterprise data, providing instant answers and insights. The platform aims to cut through digital noise, highlight important information, and help users make faster decisions. Key features include finding files quickly, getting instant answers through chat, organizing data, and instant recall. Finden integrates with existing apps and tools, consolidating digital workspaces into one secure, intelligent hub. It emphasizes data security with advanced encryption, rigorous compliance, and proactive threat protection, ensuring queries are sent to a private AI model and data is never stored or used for training.

small-text is a Python library designed for active learning in text classification, enabling efficient labeling of training data for supervised learning, especially when labeled data is scarce. It provides unified interfaces for active learning, allowing users to easily combine various query strategies with classifiers from popular libraries like sklearn, PyTorch, and transformers. The tool supports GPU-based PyTorch models and integrates with transformers for state-of-the-art text classification. It includes multiple scientifically evaluated components such as query strategies, initialization strategies, and stopping criteria, which can be mixed and matched for building active learning experiments or applications. The library is open-source and requires Python 3.9 or newer.

Parsewise is a decision platform built to assess complex risk across various workflows, including underwriting, claims, and portfolio diligence. Powered by proprietary document intelligence research from Parsewise Labs, it transforms complex, fragmented data into decision-ready insights. The platform allows users to upload documents in various formats (PDF, Word, Excel, images), query in plain English, and receive traceable insights and structured data. It features AI agents that automate extraction and analysis, reducing manual effort. Parsewise is designed for enterprise-grade security, ensuring data protection with encryption and no training on customer data. It supports various industries like Insurance & Reinsurance, Asset Management, and Regulatory & Brokers.