AI Agents & Automation

LLM-Kit is a comprehensive WebUI integrated platform designed for working with large language models (LLMs). It supports a wide array of mainstream LLM API interfaces and open-source models, making it accessible for various applications. The platform offers a full-process toolkit that includes knowledge base integration, database connectivity, and advanced features like LoRA and full-parameter fine-tuning. Users can also leverage capabilities such as role-playing, Midjourney text-to-image generation, dataset creation, and live2d integration. LLM-Kit aims to enable users to build custom models and applications without needing to write code, providing a versatile environment for AI development and deployment.

SQLBot is an intelligent data querying system developed by DataEase, leveraging large language models (LLMs) and Retrieval-Augmented Generation (RAG) technology. It empowers users to perform conversational data analysis (ChatBI), transforming natural language questions into SQL queries to retrieve data and generate visualizations. The system is designed for quick deployment, requiring only basic configuration of LLMs and data sources. Key features include high-quality Text-to-SQL conversion, robust security with workspace-level resource isolation and fine-grained data permissions, and easy integration into various applications like n8n, Dify, and DataEase. SQLBot also supports continuous improvement through custom prompts, terminology libraries, and SQL example calibration, ensuring accuracy that evolves with usage.

Readable is an AI-powered translation tool specifically designed for PDF documents, allowing users to translate files while maintaining their original layout and readability. It supports high-accuracy translation for both research and business needs, with specialized terminology handling. The tool offers unlimited translations for various document sizes, with options for English to Japanese or over 200 languages to Japanese. Key features include one-click translation, fast processing times (around 10 seconds), and a Chrome extension for online file translation. Readable utilizes its own translation engine and offers an option to use ChatGPT's translation engine for premium users. It also provides a user dictionary function for specialized terms and priority customer support for higher tiers.

AntSK is an open-source AI knowledge base and agent platform developed with .NET 9, Blazor, Semantic Kernel, and Kernel Memory. It offers a comprehensive solution for AI application development, supporting local offline AI large models and functioning without an internet connection. Key features include a Semantic Kernel for natural language processing, a Kernel Memory for continuous learning and knowledge storage, and a robust knowledge base that accepts various document formats like Word, PDF, and Excel. The platform also supports text-to-image generation with StableDiffusion, custom GPT model creation, and an open API plugin system for integration. AntSK is designed for enterprise-level AI applications, offering multi-model support, intelligent knowledge retrieval, and OCR text recognition capabilities.

Phi2-mini-Chinese is an experimental open-source project designed for training small Chinese language models from scratch, leveraging the Phi2 architecture. It provides the necessary code and model weights, allowing developers to build their own Phi2-based Chinese chat models. A key feature is its support for integration with Langchain, enabling retrieval-augmented generation (RAG) by loading local knowledge bases. The project details various stages of model development, including data cleaning, tokenizer training (both byte-level and char-level BPE), causal language model (CLM) pre-training, supervised fine-tuning (SFT), and DPO preference optimization. It also includes practical examples for implementing general conversational capabilities and RAG, making it a valuable resource for those looking to customize and deploy Chinese language models.

wenda is an open-source LLM calling platform designed for efficient content generation, particularly for individuals and small businesses with limited computing resources. It prioritizes knowledge security and privacy by integrating various capabilities. The platform supports multiple large language models, including offline deployment options like chatGLM-6B/2-6B, chatRWKV, and InternLM, as well as online API access to OpenAI API and chatGLM-130b API. A key feature is its Auto scripts, which allow for custom dialogue flows, external API access, and dynamic LoRA model switching via JavaScript plugins. Additionally, wenda offers robust knowledge base integration, supporting local offline vector libraries, local search engines, and online search engines, alongside features like conversation history management and multi-user support for internal deployment.

Isazi is a leading AI and Machine Learning solutions provider with over a decade of experience, specializing in optimizing organizations and solving complex challenges. Their offerings include Hudson, a digital twin platform for data-driven decision-making in supply chains, and Sophia, an advanced AI platform that automates workflows with augmented accuracy using human crowdsourcing for financial and healthcare services. Isazi also provides Applied AI Solutions, crafting bespoke models and deploying actionable insights across various industries, including financial services, corporate services, and supply chain management. Their team comprises over 60 scientists, mathematicians, and engineers, focusing on rigorous mathematical approaches to drive measurable results.

Domyn, formerly known as iGenius, offers an advanced AI platform designed for regulated industries, emphasizing technological sovereignty and full control over AI models, data, and infrastructure. The platform provides AI agents tailored to enterprise challenges, a composite AI platform for designing and orchestrating agents, and foundational LLMs that can be owned, adapted, and evolved by businesses. Key differentiators include air-gapped deployment for maximum security, full model ownership, and regulatory-grade compliance with complete traceability and auditability. Domyn also boasts Colosseum, one of Europe’s largest AI supercomputers, purpose-built for training trillion-parameter LLMs and executing enterprise workloads with unmatched computational power. This comprehensive ecosystem ensures privacy, auditability, and independence from external providers, making it ideal for high-stakes environments.

Qode is an AI recruiting engine designed to streamline and scale the hiring process for enterprises. It centralizes the entire hiring lifecycle, replacing disconnected tools with a single platform for speed, precision, and efficiency. Key features include AI search builders with advanced filters for sourcing, smart candidate ranking, and built-in outreach sequences. The platform also offers AI-assisted job description creation, job distribution to over 200 hiring platforms, and an Application Tracking System (ATS). Qode provides AI-led interviews with CV-tailored technical and behavioral assessments in over 30 languages, generating structured reports with video, transcript, and integrity signals. It aims to make hiring decisions more precise, fair, and consistent by prioritizing objective data and merit.

Paperbox is an AI-powered insurance automation platform designed to significantly reduce administrative work for insurance professionals. It automates claims and policy intake, streamlining back-office operations by handling email classification, task creation, and client communications 24/7. Key features include instant mail-to-task automation, real-time sentiment analysis, intelligent response handling, and document classification and archiving. The platform integrates with legacy insurance systems and provides real-time insights into business data, helping with client retention and churn prevention. Paperbox aims to free up insurance professionals to focus on higher-value tasks and client interactions, offering immediate ROI through increased efficiency and reduced manual data entry.

TitleWize is an AI-powered legal-tech platform designed to enhance property due diligence and establish trust in real estate transactions, specifically in India. It offers advanced risk assessment capabilities, streamlines acquisition pipelines, and helps manage property inventory. By leveraging artificial intelligence, TitleWize aims to transform the traditional property due diligence process, ensuring that critical details are not overlooked. This platform is ideal for legal and acquisition teams seeking to make informed decisions and mitigate risks in the complex real estate market.

Well Embed provides an AI-native infrastructure for automated invoice and receipt retrieval, designed to power products with essential financial data. It offers full coverage with connectors for various customer channels, including email, chat apps, cloud storage, and portals, ensuring everything is captured automatically. The platform extracts structured data from invoices and receipts, turning products into financial powerhouses through its suite of APIs and connectors. It handles ingestion, formatting, and source detection through a unified API, allowing for quick integration and deployment. Well Embed also offers options to monetize retrieval within products, providing flexible pricing models for businesses of all sizes.

ChatLLaMA is an innovative AI tool that empowers users to develop personalized AI assistants directly on their GPUs. Leveraging LoRA weights, which are trained on Anthropic's HH dataset, ChatLLaMA facilitates natural and seamless conversations between the AI assistant and users. The platform is available for 30B, 13B, and 7B models, with an RLHF version of LoRA anticipated soon. It is designed for research purposes and encourages community contributions of high-quality dialogue-style datasets for further training. ChatLLaMA also offers opportunities for developers to contribute to open-source AI software and apps, providing GPU power in exchange for coding assistance.

rag-web-ui is an intelligent dialogue system built on Retrieval-Augmented Generation (RAG) technology, designed to create smart Q&A systems from custom knowledge bases. It combines document retrieval with large language models to deliver accurate and reliable knowledge-based question answering. The system supports various LLM deployment options, including cloud services like OpenAI, DeepSeek, and MiniMax, as well as local models via Ollama, catering to diverse privacy and cost needs. It features intelligent document management with support for multiple formats, automatic chunking, and vectorization. The advanced dialogue engine offers precise retrieval, multi-turn contextual dialogue, and reference citations. It also provides OpenAPI interfaces for seamless knowledge base access.

PDFConvo transforms how users interact with PDF documents by leveraging advanced AI technology. This platform enables direct conversation with PDFs, allowing users to ask questions, obtain instant summaries, and extract key insights efficiently. It features AI Analysis for deep document understanding, Smart Search using natural language queries, and Quick Insights for automatic summarization. Designed to save time, PDFConvo processes documents significantly faster than manual reading. It offers various pricing plans, including a free trial, and supports unlimited PDFs and AI-powered chat capabilities across all tiers. The tool also highlights its ability to help users understand, analyze, and extract information from any PDF document in seconds.

Karya designs and delivers end-to-end pipelines for data, evaluation, and deployment in AI. The platform offers custom data solutions, including domain-specific transcription, localized translation, and large-scale multimodal dataset creation. Karya also provides comprehensive evaluation ecosystems, combining public feedback with expert judgment to test model performance across real-world contexts, languages, and high-impact use cases. Additionally, it offers diverse, high-quality, human-generated, and verified off-the-shelf datasets for ASR, TTS, Embodied, and Physical AI, allowing users to browse a catalogue of ready-to-use data.

Briink is an AI-powered platform designed to transform ESG document analysis for sustainability teams. It leverages generative AI to extract and analyze unstructured ESG data from various documents, including annual reports, financial statements, and websites. The tool automates the pre-filling of ESG questionnaires for frameworks like CDP and ESRS, ensuring data accuracy with full source references. Briink also facilitates supplier and portfolio analysis, ESG ratings and regulations compliance, and benchmarking against peers. It offers features like multi-document uploads, responsible AI with human-in-the-loop, and an API for seamless platform integrations. Briink aims to streamline complex ESG workflows, reduce manual effort, and enable data-driven decision-making for sustainable value creation.

Cognee is an open-source AI memory engine designed to enhance AI infrastructure by uncovering hidden connections within data. It serves as a knowledge engine that learns and adapts from feedback, replacing custom knowledge graphs and vector stores with a unified platform. Cognee supports over 38 data types and integrates with 12+ agentic frameworks, offering features like context curation, personalization, tool management, and custom data models. It's ideal for building vertical AI agents, unifying data silos, and creating local agent memory, learning from feedback to deliver better answers over time. The platform is trusted in production across various industries, from regulated environments to startup stacks.

The shadcn-ui-mcp-server is a Model Context Protocol (MCP) server designed to give Large Language Models (LLMs) comprehensive context on shadcn/ui v4 component structure, usage, and installation. It enables AI assistants to seamlessly retrieve component source code, demos, and metadata for various frameworks including React, Svelte, Vue, and React Native. Key features include multi-framework support, access to component source code and demos, block implementations (dashboards, calendars, forms), metadata access (dependencies, descriptions), directory browsing, smart caching for GitHub API integration, and Server-Sent Events (SSE) transport for multi-client deployments. The server is Docker-ready for production environments and offers quick installation options, including a one-click setup for Claude Desktop. It significantly enhances AI-powered development by facilitating component discovery, multi-framework learning, rapid prototyping, and accurate code generation with proper dependencies.

The PAN OCR API by AZAPI.ai leverages advanced OCR technology to swiftly and accurately extract data from PAN cards. This service is designed for businesses and organizations requiring quick and precise data extraction, seamlessly capturing details such as the PAN number, name, father's name, and date of birth. It is ideal for identity verification, streamlining financial processes, and managing records, ensuring data privacy and security in compliance with legal and regulatory standards. By integrating this API, users can significantly reduce manual data entry errors, save time, and improve the accuracy of their processes, benefiting sectors like finance, government, and customer onboarding.

NirixAI is an AI-powered learning assistant designed to help students, professionals, and lifelong learners study smarter. It transforms passive content like YouTube videos, PDFs, Microsoft Word files, Excel spreadsheets, and Markdown files into active learning experiences. Users can paste a YouTube URL or upload documents to get AI-powered summaries, generate quizzes, receive personalized explanations, and ask questions for instant answers. The tool adapts explanations to the user's level, remembers context across sessions, and focuses on understanding and retention. NirixAI aims to make AI-powered learning accessible, offering a 21-day free trial and affordable paid plans.

Sola Solutions is an agentic process automation platform that leverages LLMs and computer vision to automate data entry, scraping, and processing flows. It offers a new era of automation, moving beyond traditional RPA limits with adaptive, insightful, and tailored solutions for enterprises. Sola provides the fastest time-to-value, allowing users to create fully automated workflows from screen recordings in minutes. Its flexible automations learn and adapt, reducing build and maintenance time, while intuitive no-code tooling empowers business users to build and maintain processes. The agentic engine learns, makes decisions, and self-optimizes in real-time for intelligent automation. Key capabilities include AI-powered workflow generation, adaptive automations, powerful integrations, a visual workflow editor, transparent monitoring, and API support.

DecoverAI is an AI-powered legal discovery platform designed to simplify and accelerate the entire litigation lifecycle for law firms and in-house legal teams. It automates critical tasks such as document classification, privilege review, redaction, and production, enabling teams to focus on strategy rather than manual sorting. The platform boasts an 80% reduction in review time by classifying documents for responsiveness, privilege, and confidentiality, with production ready in under an hour, including Bates numbering, redaction, and privilege logging. DecoverAI ensures full attorney control, allowing review and override of all AI classifications and redactions. It is SOC 2 compliant, offering enterprise-grade security and full audit trails, and supports various stages of litigation including eDiscovery, early case assessment, internal investigations, and trial preparation.

Parambil delivers AI-assisted medical record review software specifically designed for mass tort and complex litigation workflows. Trusted by both plaintiff and defense firms, the platform significantly accelerates and enhances the accuracy of medical record analysis. It generates comprehensive chronologies, validates cases, and provides analytic insights, having reviewed over 5 million records with 44% more correct data and 95% faster than traditional methods. Key features include AI Agents for multi-step reasoning and document drafting, a Provider Guide for clinician organization, and tools for identifying missing data. Parambil also offers legal document drafting, live web search for clinical guidelines, and interactive data visualization for medical records.