AI Agents & Automation

AI2-THOR is an open-source platform developed by the Allen Institute for AI (AI2) designed for Visual AI research. It offers a near photo-realistic and interactable framework for embodied AI agents, supporting research in common sense reasoning. The platform includes various environments such as iTHOR for high-level interaction, ManipulaTHOR for visual object manipulation with robotic arms, and RoboTHOR for Sim2Real research with simulated and physical world counterparts. It features over 200 custom-built scenes, 2600+ heavily annotated household objects with realistic physics, and multiple agent types including multi-agent support, LoCoBot, and Kinova 3 inspired robotic manipulation agents. AI2-THOR also provides 200+ actions for interaction and navigation tasks, first-class support for various image modalities (RGB, instance/semantic segmentation, depth, normals), and extensive metadata for complex reward functions.

Papermerge DMS is an open-source document management system designed for digital archives, allowing users to store, organize, and index scanned documents in PDF, JPEG, and TIFF formats. It features optical character recognition (OCR) to add searchable and selectable text to image-only documents, supporting over 100 languages. The system includes document versioning, ensuring original uploads are retained while new versions are created for operations like OCR. Users can define custom fields for documents and categorize them into types like "Receipt" or "Invoice." Page management features enable reordering, rotating, and extracting pages to correct scanning errors. Papermerge DMS offers a user-friendly, modern web interface to boost productivity.

Positive Reframing is an AI chatbot designed to offer positive perspectives and assist users in reframing negative thoughts. While the live website currently shows a build error, the tool's intended purpose is to serve as a conversational AI for educational use, creative writing prompts, and personal well-being. It aims to help users develop a more optimistic outlook by guiding them through positive reframing techniques. The tool is expected to be available for free, making it accessible for a wide range of users looking for support in mental well-being or creative inspiration.

GPT OSS WebGPU provides a unique solution for running the GPT-OSS-20B language model directly within your web browser. This innovative tool leverages WebGPU technology, ensuring that all model computations occur locally on your device, thereby removing any dependency on external servers. Users can type any prompt and receive an instant continuation generated by the 20-billion parameter model. This local execution capability is particularly beneficial for developers, researchers, and enthusiasts who wish to experiment with large language models without concerns about data privacy or server costs. It offers a convenient and accessible way to interact with a powerful AI model directly from a web interface.

Profimatix is an AI-powered revenue super agent designed to empower sales and revenue teams. It captures sales touchpoints across meetings, emails, calls, and CRMs, learning what works to maximize revenue. The platform automates CRM updates, schedules follow-ups, and identifies next steps, significantly reducing sales cycles. Profimatix offers real-time call assistance with AI suggesting talking points and objection handling, alongside intelligent follow-ups. It also provides revenue analytics to uncover top revenue leaks and drivers, helping teams refine strategies and deliver accurate forecasts. The tool aims to make CRMs always accurate and provide data-backed recommendations for growth.

Text to Survive is an application designed to facilitate interaction with the Mistral API. It functions by forwarding user-provided chat requests to the Mistral API and subsequently returning the API's response. To use the application, users are required to submit their chat requests in a JSON payload format. In return, they will receive a JSON response directly from the Mistral API. This tool acts as a straightforward intermediary, enabling developers and users to integrate and test Mistral's conversational AI capabilities within their own projects or workflows by handling the communication protocol.

Mindpip is an AI-powered customer support platform designed to enhance customer experience, reduce response times, and significantly cut support costs. It offers a hybrid customer service widget that integrates both human and AI agents, allowing AI to handle common questions while human agents focus on complex issues. Key features include quick escalation of issues, AI agent training from various sources like websites and documents, and customizable widgets to match brand identity. The platform also emphasizes enterprise-grade security for customer data and provides a 7-day free trial for most plans.

Langcorn is an open-source API server designed to simplify the deployment of LangChain Large Language Model (LLM) applications and agents. Leveraging the high-performance FastAPI framework, Langcorn automates the serving process, making it easier for developers to operationalize their LLM solutions. Key features include easy deployment of LangChain models and pipelines, ready-to-use authentication functionality, and scalable architecture for language processing applications. It supports custom pipelines, asynchronous processing for faster response times, and provides well-documented RESTful API endpoints. Langcorn also allows for overriding default LLM parameters per request and handling memory for conversational AI applications, making it a versatile tool for LLMops.

Next Example App is a straightforward AI application hosted on Hugging Face Spaces, designed for generating responses based on user input. Users can simply type their text into a designated box, and the application will process it to provide a corresponding output. This tool serves as a practical example of an AI agent, demonstrating basic conversational or text-generation capabilities. Its simplicity makes it accessible for general users and students who are exploring AI interactions or require automated text-based support. The application focuses on a direct input-output mechanism, making it easy to understand and use for quick text-based tasks.

ProfilePro by Merchynt is a free AI SEO Chrome Extension designed to optimize Google Business Profiles for improved local search rankings. This tool automates various GBP management tasks, including generating SEO-optimized review responses, crafting business descriptions, and creating engaging Google Business posts. Users can also generate AI images for their posts and receive suggestions for business categories and service descriptions. ProfilePro supports multiple languages, making it accessible to a broader audience. It aims to simplify local SEO for small businesses, helping them rank higher on Google Maps and local Google search results with minimal effort.

Nfig is an AI-powered platform designed for real-time enterprise knowledge and secure configuration management. It leverages artificial intelligence to provide context-aware answers, helping organizations streamline their operations and ensure compliance. The tool facilitates team collaboration by centralizing knowledge and configuration data, making it accessible and manageable for all relevant stakeholders. Nfig is particularly useful for maintaining consistent and secure environment configurations across an enterprise, reducing manual errors and improving efficiency. Its capabilities extend to assisting with regulatory compliance by offering intelligent insights and management features for critical configurations.

Prompt Refine was a dedicated tool for enhancing prompt engineering workflows, allowing users to methodically improve their Large Language Model (LLM) prompts. It integrated with various AI models, including OpenAI, Anthropic, Together, and Cohere, providing a versatile environment for prompt development. Key functionalities included comprehensive history tracking to analyze and compare different prompt runs, enabling users to refine their approaches based on past results. The platform also supported the creation and reuse of variables within prompts, streamlining the experimentation process. Users could export their experiments to CSV for further analysis, making it a valuable asset for data-driven prompt optimization. However, the tool has since been shut down.

Beam AI provides a leading platform for agentic automation, enabling enterprises to deploy self-learning AI agents for various operations. It helps reduce operational costs, increase efficiency, and transition organizations into AI-native market leaders. The platform supports building and deploying agents quickly, integrating with over 1000 systems including SAP and Salesforce. Beam AI agents are designed for enterprise scale and security, offering continuous learning, human-in-the-loop capabilities, and no-code development. It ensures secure, compliant, and auditable operations, meeting GDPR, ISO 27001, and SOC 2 Type II standards, with flexible deployment options including cloud and on-premise.

Qinglong is an AI tool hosted on Hugging Face Spaces, which appears to be designed for task automation, educational assistance, and content generation. However, the application is currently paused, and users are directed to the community tab to request its restart from the author. While the exact functionalities are not detailed due to its paused status, its categorization suggests capabilities in AI agents and conversational AI. The tool was previously available for free on the Hugging Face platform.

Gemma3 is a chat web application that runs Gemma 3 models entirely within the browser, offering a seamless and instant conversational AI experience. Users can type messages into a simple chat window and receive natural-language replies from the AI model. This tool is ideal for developers, researchers, and AI enthusiasts who want to experiment with Gemma models without complex setups. Its in-browser operation makes it highly accessible, allowing for quick interactions and testing of AI capabilities directly from a web browser. The application focuses on providing a straightforward interface for engaging with advanced AI models.

SymbolicAI is a neuro-symbolic framework designed to integrate classical Python programming with the programmable nature of Large Language Models (LLMs). It emphasizes a modular and extensible design, allowing users to easily create custom engines, host local models, and interface with external tools like web search or image generation. The framework introduces 'Symbol' objects, which can operate in either syntactic (normal Python value) or semantic (neuro-symbolic engine-wired) modes, enabling complex chains of operations. A key differentiator is its implementation of Design by Contract principles for LLMs, helping to build correctness directly into the design through decorators, data models, and validation constraints to mitigate hallucination.

The open-trading-api GitHub repository offers comprehensive sample code for integrating with the Korea Investment & Securities (KIS) Open API. Designed for both Python developers and LLM-based automated trading environments, it simplifies the process of understanding and utilizing the KIS API. The repository includes functional unit samples for LLMs, practical API call examples for users, a strategy builder with visual UI, and a backtesting engine. It supports various API categories including domestic and overseas stocks, bonds, futures, options, ELW, and ETF/ETN. The tool aims to reduce development burden and facilitate the creation of AI-driven trading strategies and automated systems.

Agentation is an open-source, agent-agnostic visual feedback tool designed to assist AI coding agents. It enables users to click and annotate elements on a webpage, select text, or define specific areas, generating structured output that helps AI agents identify exact code references. The tool features automatic selector identification, multi-select and area selection capabilities, and an animation pause function to capture specific states. It provides structured markdown output including selectors, positions, and context, and supports both dark and light modes. Agentation is built with zero dependencies, using pure CSS animations, and requires React 18+ and a desktop browser.

Multi-Agent-Reinforcement-Learning-Environment is an open-source GitHub repository offering a collection of Python environments designed for multi-agent reinforcement learning research and development. The repository includes various toy problems such as Multi Agent Soccer Game, Multi Agent Rescue, Multi Agent Cleaner, and Multi Agent Move Box, among others. It also provides single-agent versions of some environments, making it suitable for testing and developing reinforcement learning algorithms. Each environment comes with dedicated documentation in PDF format. The environments are designed with a standard assumption of synchronous agent operation and provide clear member functions for resetting, stepping through actions, and observing states, making them accessible for researchers and developers in the field.

Fuel is an open-source data pipeline framework specifically designed for machine learning applications, developed primarily for use with Blocks, a Theano toolkit for training neural networks. It provides interfaces to common datasets like MNIST, CIFAR-10, and Google's One Billion Words, enabling users to easily access and manage diverse data sources. The framework supports flexible data iteration, allowing for minibatches with shuffled or sequential examples. A key feature is its pipeline of preprocessors, which facilitates on-the-fly data manipulation such as adding noise, extracting n-grams, or patching images. Fuel emphasizes serializability with pickle, ensuring that entire pipelines can be checkpointed and resumed for long-running experiments, relying heavily on the picklable_itertools library.

Ratchet + Phi is an AI chatbot tool hosted on Hugging Face Spaces, designed for users to interact with the Phi-3 language model. Users can input questions or instructions into a prompt box, load the Phi-3 model, and run it to receive AI-generated text responses. This application serves as an accessible platform for exploring the functionalities of the Phi model, making it suitable for educational purposes, research, and general experimentation with conversational AI. It offers a straightforward interface for engaging with advanced language model capabilities.

Qwen-2.5 WebLLM offers a conversational AI experience by enabling direct interaction with a language model within your web browser. This tool is designed to generate responses tailored to your specific input, with the unique advantage of running all operations locally on your device. This local execution ensures privacy and potentially faster response times, as data does not need to be sent to external servers. It's an accessible way to engage with AI, providing a platform for conversational AI research, development, and general question answering without the need for complex setups or cloud services. The tool is open-source and available for free, making it suitable for educational purposes and personal exploration of large language models.

Gemma-3-R1984-27B ChatBot is an AI-powered application designed to provide answers by analyzing various document types, including text, PDF, CSV, and TXT files. Users can upload their documents and then ask questions, receiving detailed responses derived directly from the content. This tool is built for reasoning and deep research, leveraging the Gemma-3 family of models. It is hosted on Hugging Face Spaces and benefits from the processing power of NVIDIA H100 GPUs, indicating a focus on robust performance for complex analytical tasks. The application aims to streamline information extraction and question-answering from diverse data sources.

NAGISystem is an innovative AI agent tool hosted on Hugging Face Spaces, designed to evaluate user proposals. Users submit a proposal, and the system leverages three distinct AI personas—MELCHIOR, BALTHASAR, and CASPER—to cast individual votes for approval or denial. The ultimate decision is determined by a majority vote among these AI agents. This system offers a novel approach to decision support, providing an interactive and engaging way to get AI-driven feedback on ideas or proposals. It's a free-to-use application, making AI-powered evaluation accessible to a broad audience.