AI Agents & Automation

Agentset is an open-source platform designed for building, evaluating, and deploying production-ready Retrieval Augmented Generation (RAG) and agentic applications. It provides comprehensive end-to-end tooling, covering ingestion, chunking, embeddings, and retrieval processes. The platform is model-agnostic, allowing users to integrate their preferred LLM, embeddings, and vector database. Key features include a chat playground with message editing and built-in citations, production hosting with preview links and custom domains, and a developer-friendly API with typed SDKs and OpenAPI specifications. Agentset also supports multi-tenancy and is built with modern technologies like TypeScript, Next.js, AI SDK, Prisma, Supabase, and Trigger.dev, making it a robust solution for developers.

Visspot is an AI-powered tool designed to transform diverse content formats, including links, images, documents, and videos, into an intelligent knowledge base. This platform eliminates the need for coding, allowing users to quickly create and manage a Q&A knowledge base. It leverages AI to process and organize information, making it easily retrievable and usable for various applications. Visspot aims to simplify the creation of comprehensive knowledge repositories, enabling efficient information management and retrieval without technical expertise.

apple-docs-mcp functions as a Model Context Protocol (MCP) server, specifically designed to integrate Apple Developer Documentation with AI assistants such as Claude, Cursor, VS Code, Windsurf, Zed, Cline, and Amazon A Developer CLI. It offers intelligent search across various Apple frameworks like SwiftUI, UIKit, Foundation, and ARKit, providing full access to Apple's JSON API for documentation, Swift/Objective-C APIs, and WWDC videos with transcripts. Developers can explore framework indexes, technology catalogs, and sample code libraries, making it an invaluable resource for AI-powered development environments. The tool also tracks documentation updates, beta APIs, and platform compatibility, enhancing the efficiency of accessing Apple's extensive developer resources.

aisearch-openai-rag-audio is an open-source sample implementation of the VoiceRAG pattern, designed to create interactive voice generative AI experiences. This tool leverages Azure AI Search for retrieval-augmented generation (RAG) and Azure OpenAI's gpt-4o-realtime-preview model for real-time audio processing and response generation. It enables developers to build applications with voice interfaces that capture audio input, process it through a RAG system, and generate audio output. Key features include voice input/output, RAG capabilities for answering questions from a knowledge base, and citations for search results. The project provides infrastructure as code and a Dockerfile for deployment to Azure Container Apps, and can also be run locally, making it a flexible solution for developers looking to integrate advanced voice AI into their applications.

ApeRAG is a production-ready RAG (Retrieval-Augmented Generation) platform designed for building sophisticated AI applications. It integrates Graph RAG, vector search, and full-text search with advanced AI agents. Key features include five comprehensive index types (Vector, Full-text, Graph, Summary, Vision) for multi-dimensional document understanding, intelligent AI agents with MCP tool support, and enhanced Graph RAG with entity normalization. The platform also offers complete multimodal document processing, a hybrid retrieval engine, and MinerU integration for advanced document parsing. ApeRAG provides enterprise-grade management features, full Kubernetes support with Helm charts, and KubeBlocks integration for simplified deployment of production databases.

LangDrive & Addy AI provides specialized AI tools for data management and customer service. LangDrive is designed to enhance data management within Google Drive using AI capabilities, aiming to streamline how users interact with and organize their data. Addy AI, on the other hand, is tailored for the e-commerce sector, offering AI-driven customer service solutions to improve efficiency and customer satisfaction. Together, these tools aim to leverage artificial intelligence to optimize data handling and elevate customer support operations for businesses.

LIDIA is a comprehensive AI ecosystem specifically designed for legal professionals, offering an integrated platform for legal research, analysis, and decision-making. Developed by experienced lawyers, LIDIA applies advanced technology to legal work with the goal of enhancing quality, reducing errors, and supporting professional reasoning. It acts as a co-thinker, not an automation tool, for complex and high-responsibility tasks. Key features include organizing internal studio knowledge for AI querying, extending and validating information through official sources, guiding decision-making with AI agents, and integrating AI directly into document drafting and revision within Word. LIDIA also offers specialized AI agents for legal workflows, a Smart Answer function for natural language queries on archived documents, and a Workflow Builder for custom legal processes.

WebQuery is an AI-powered tool designed to enhance web understanding by allowing users to interact directly with online articles. Users can upload single or multiple links, and the platform processes the content to create a conversational interface. This enables users to ask questions about the article's content, with ChatGPT's AI providing detailed answers based on the information within the registered links. This feature is particularly useful for quickly extracting necessary information, gaining new perspectives, and achieving a deeper understanding of articles without needing to read them in their entirety. It offers both a free basic plan and a premium subscription for more extensive use.

Fineksi provides an AI-powered cognitive document automation platform specifically designed for financial institutions. It streamlines the credit process by automatically extracting, classifying, and processing credit-related documents with high accuracy. The platform incorporates advanced AI and machine learning models for fraud detection, identifying document manipulation, alterations, and anomalous transactions. Fineksi also offers intelligent credit analysis, providing smart risk assessments and predictive insights for optimal decision-making. Its infrastructure is built with a layered defense approach to ensure data protection, and it delivers insights in minutes, significantly accelerating workflows and reducing human error. Fineksi is trusted by banks, multifinance companies, and P2P lending platforms to enhance productivity and accuracy in credit underwriting.

VectorShift is an end-to-end AI automations platform designed for building, deploying, and managing AI applications and workflows. It caters to both non-technical users with an intuitive drag-and-drop no-code interface and developers with a robust Code SDK, ensuring complete interoperability between the two. The platform supports various data formats, including websites, documents, videos, and audio, and integrates with popular tools like Google Drive, Salesforce, and Notion. Users can leverage pre-built templates, access leading large language models, and automate tasks such as report generation, chatbot deployment, and marketing copy creation.

All-In-OneNote is an AI-powered OCR tool designed to streamline the process of digitizing and organizing notes within Microsoft OneNote. It specializes in converting various document types, including handwritten notes, PDFs, Word documents, and e-Ink documents, into editable text. This capability allows users to easily search, edit, and manage their notes directly within OneNote, enhancing productivity and knowledge management. The tool offers a free plan with three conversions, making it accessible for users to try out its AI-driven handwriting recognition and document conversion features before committing to a paid plan. It's ideal for anyone looking to integrate their physical and digital notes seamlessly into OneNote.

ai-pdf-chatbot-langchain is an open-source AI chatbot agent built with LangChain and LangGraph, designed to ingest PDF documents, store their embeddings in a vector database (like Supabase), and answer user queries using OpenAI or other LLM providers. This monorepo serves as a customizable template, offering features such as document ingestion, retrieval graphs for intelligent question answering, and real-time streaming responses. It includes a Next.js frontend for file uploads and chat, and a Node.js/TypeScript backend orchestrating the AI logic. The project emphasizes LangGraph integration for visualizing and debugging agentic workflows, making it a robust solution for developers looking to build sophisticated PDF-aware chatbots.

APTO, Inc. provides harBest, a comprehensive platform designed to streamline AI development from data collection to model evaluation. harBest simplifies the crucial process of creating high-quality 'teacher data' through annotation, which is vital for AI success. The platform leverages a network of skilled cloud workers to ensure speedy and accurate data creation, offering both a SaaS solution and expert services. It helps businesses overcome the initial hurdles of AI adoption, such as cost and technical literacy, by providing a structured approach to data preparation. harBest also aims for long-term cost reduction by outsourcing data collection and annotation, allowing internal teams to focus on core tasks. The platform supports various data types including images, videos, and audio, catering to diverse applications like IoT, anomaly detection, and e-commerce recommendations.

File Concat Tool is a free online utility designed to combine multiple code files, documents, and folders into an optimized format for various AI assistants, including ChatGPT, Claude, Gemini, and other LLMs. It ensures 100% secure offline processing, meaning your files never leave your device. The tool features a user-friendly drag-and-drop interface and supports GitHub repository integration, making it ideal for developers. Key functionalities include token usage estimation, multiple output formats, smart file processing, and dark mode support, all aimed at optimizing content for AI context windows. It's a valuable resource for prompt engineering and codebase sharing.

CustomGPT.ai is a no-code platform designed for businesses to create custom AI agents (GPTs) trained on their specific content. It allows users to upload documents in over 1400 formats, ingest website content, and integrate with more than 100 sources like Google Drive, HubSpot, WordPress, and Shopify. These AI agents can handle up to 93% of support and research questions, delivering exceptional customer experiences and maximizing employee efficiency. The platform emphasizes data security with SOC2 Type 2 compliance and GDPR adherence, ensuring user data is never used to train LLMs. It supports 92 languages, making it suitable for global audiences.

Ordinal is an AI-powered research assistant specifically designed for local governments, enabling staff to find and share consistent, accurate answers in seconds. The platform scans approved documents such as municipal codes, GIS data, and meeting notes, providing precise information and references instantly. It helps save time by reducing research efforts, transfers institutional knowledge by ensuring access to reliable information even with staff changes, and aids in training new staff with self-service learning. Ordinal also features a resident AI chatbot, a legislation monitor, a grant finder, and a report assistant, making it a comprehensive solution for various government departments.

rag-cookbooks is a comprehensive, open-source repository dedicated to advanced and agentic Retrieval-Augmented Generation (RAG) techniques. It serves as a valuable resource for researchers and developers looking to implement and evaluate sophisticated RAG systems. The repository progresses from naive RAG to more complex methods, offering clear implementations and explanations for each technique. It also includes research papers and references for further reading. Key features include various RAG techniques like Hybrid RAG, Hyde RAG, Parent Document Retriever, RAG fusion, Contextual RAG, Rewrite Retrieve Read, Unstructured RAG, and several agentic RAG approaches such as Basic Agentic RAG, Corrective RAG, Self RAG, Adaptive RAG, and ReAct RAG. The repository also provides guidance on RAG evaluation, often integrating with Athina AI for end-to-end implementation and assessment.

RHIA Copilot is an AI-powered recruitment platform designed to modernize the hiring process for HR teams. It automates sourcing, pre-selection, and candidate-job matching with explainable AI, ensuring GDPR compliance and results-oriented outcomes. Key features include assisted sourcing (Hunter) to fill pipelines with qualified candidates, intelligent application tracking, and explainable matching with scoring across five axes to reduce false positives by 35%. The platform also facilitates recruiter-manager collaboration, generates job briefs and announcements in minutes, and provides real-time insights and dashboards to track pipeline performance and ROI. RHIA Copilot aims to give recruiters back time by centralizing analysis, automating documentation, and streamlining the entire recruitment workflow.

6Estates is an AI-driven intelligence company providing comprehensive Enterprise AI solutions tailored for business needs, particularly in the financial services sector. Spun off from a joint research center involving the National University of Singapore and Tsinghua University, 6Estates offers AI applications like Intelligent Document Processing (IDP) for unlocking complex, unstructured documents, Finance-As-A-Service (FAAS) for automating lending workflows, and Financial Statement Analyzer (FSA) for automated financial statement analysis. Beyond applications, they provide LLM Agency for customized, robust multimodal and multilingual LLMs, supporting both public API and on-premise deployment. Additionally, 6Estates offers cost-effective GPU Cloud services, ensuring access to cutting-edge cloud resources at competitive prices in Southeast Asia.

Bahama provides an agent-first AI cloud infrastructure, enabling AI agents to deploy web applications, provision databases, and manage storage effortlessly. It integrates with existing AI coding tools like Claude Code, Cursor, and Codex via an MCP server, allowing agents to build and ship infrastructure-ready apps from the start. Bahama handles the orchestration behind the scenes, ensuring projects are isolated, resources are managed, and deployed apps run at scale. Key features include secure project management, managed SQL databases, storage buckets for assets, and secure secret management, all designed to automate the last mile of app development for AI agents.

Tianji is an open-source project dedicated to creating large language models adept at understanding and navigating traditional social scenarios. It provides comprehensive tutorials and implementations across various AI development aspects, including prompt engineering, RAG (Retrieval-Augmented Generation) knowledge bases, intelligent agent development, and LLM fine-tuning. The platform supports integration with popular models like ChatGPT, ZhipuAI, ERNIE, DeepSeek, InternLM, and Qwen, allowing for both online and local deployment. Tianji offers practical applications such as knowledge base dialogue systems for social etiquette, agent applications with tool-calling capabilities, and tools for data manufacturing and cleaning of social interaction corpora. It aims to equip users with full-stack application development skills for large language models.

CleeAI LKM™ (Large Knowledge Model) is an infrastructure layer designed to sit above your existing LLM stack, addressing critical enterprise AI challenges. It focuses on eliminating AI waste by routing queries to the most cost-effective models, enforcing verified accuracy by grounding answers in confirmed sources and blocking unconfirmed responses, and preventing data leakage through robust governance guardrails. The LKM intercepts requests before they reach the model, evaluates intent against compliance policies, and provides a full audit trail for every query. This ensures compliant AI outputs at scale, particularly in regulated industries where AI failure can lead to significant liabilities.

Aix-DB is an intelligent data analysis system built on large language models and RAG technology, designed to transform natural language queries into actionable data insights. It leverages the LangChain/LangGraph framework and a multi-agent collaboration architecture (MCP Skills) to provide end-to-end solutions for data extraction and visualization. Key capabilities include intelligent Q&A, Text2SQL for data querying, table Q&A, deep data exploration, and automated data visualization. The system emphasizes ease of use, security, and integration, offering features like a 'Skill Mode' for customized functionalities and an 'OpenClaw' intelligent integration. It supports various data sources and provides a structured workflow from user input to visualized results, making complex data analysis accessible through conversational interfaces.

deepseek4j is a comprehensive Java SDK designed for integrating DeepSeek AI models, including the R1 and V3 series, into Java applications. It provides robust capabilities such as dialogue reasoning, function calling, and the generation of JSON structured output. Additionally, it supports embedding vector generation through an OpenAI-compatible API. The SDK features a Spring Boot Starter module, enabling rapid integration with popular Java web frameworks like Spring Boot 2.x/3.x and Solon. This starter offers out-of-the-box configuration, automatic client instance wiring, and convenient support for streaming responses, simplifying the development of AI-powered applications in Java environments.