AI Agents & Automation

Static-to-Dynamic-LLMEval is the official GitHub repository for a paper detailing recent advances in large language model benchmarks, specifically focusing on data contamination. The project conducts an in-depth analysis of existing static-to-dynamic benchmarking methods designed to reduce data contamination risks. It examines methods that enhance static benchmarks, identifies their limitations, and highlights the critical gap in standardized criteria for evaluating dynamic benchmarks. The repository proposes optimal design principles for dynamic benchmarking and analyzes the limitations of current dynamic benchmarks, offering a comprehensive overview of advancements in data contamination research and guiding future efforts.

system-prompts-and-models-of-ai-tools is a comprehensive open-source GitHub repository that curates system prompts, internal tools, and AI models from a wide array of AI applications. This resource is invaluable for developers, researchers, and AI enthusiasts looking to understand the underlying mechanics and prompt engineering strategies of popular tools like Augment Code, Claude Code, Cursor, Devin AI, NotionAI, Perplexity, and many others. It provides a centralized location to explore how different AI systems are structured and prompted, fostering learning and innovation in the AI development community. The repository also highlights the importance of securing AI systems against prompt injection and extraction risks.

Kubeflow Trainer is a Kubernetes-native distributed AI platform designed for scalable large language model (LLM) fine-tuning and training of AI models. It supports various frameworks such as PyTorch, MLX, HuggingFace, DeepSpeed, JAX, and XGBoost. The platform integrates MPI into Kubernetes, facilitating efficient multi-node, multi-GPU distributed jobs across high-performance computing (HPC) clusters. This setup ensures high-throughput communication crucial for large-scale AI training requiring rapid synchronization between GPU nodes. Kubeflow Trainer also integrates with the Cloud Native AI ecosystem, including Kueue for topology-aware scheduling and multi-cluster job dispatching, and JobSet/LeaderWorkerSet for AI workload orchestration. It features a distributed data cache for zero-copy transfer of large-scale data directly to GPU nodes, optimizing memory efficiency and GPU utilization. AI practitioners can leverage the Kubeflow Python SDK to develop and fine-tune LLMs using the Trainer APIs: TrainJob and Runtimes.

Outfitz is an AI-powered outfit generator designed to provide personalized style recommendations. This tool acts as an AI stylist, helping users discover new fashion combinations and styles tailored to their individual preferences. It aims to simplify the process of choosing outfits by offering intelligent suggestions. Fashion enthusiasts looking for inspiration or those who want to explore different looks will find Outfitz beneficial for enhancing their wardrobe and personal style.

Flavorithm is an AI-powered platform designed to inspire simple, clutter-free cooking by providing weekly curated recipe recommendations, themed recipe collections, and featured food articles. Users can sign up for a free account to personalize their experience, save favorite recipes, and build a taste profile to receive more relevant weekly picks. The platform offers a variety of recipes categorized by mealtime, global flavors, baked goods, drinks, special diets, and cooking styles. It also highlights quick and easy options, including air fryer and pressure cooker recipes, making it suitable for busy individuals looking for creative and convenient meal ideas.

Weighted-Boxes-Fusion is a comprehensive Python library designed for advanced object detection tasks, specifically focusing on ensembling bounding boxes from multiple models. It offers implementations of several key methods, including Non-maximum Suppression (NMS), Soft-NMS, Non-maximum weighted (NMW), and its namesake, Weighted Boxes Fusion (WBF). The WBF method is highlighted for providing superior results compared to other ensembling techniques. The library supports various dimensions, with specific functions for 3D boxes and 1D line segments, the latter being particularly useful for Natural Language Processing (NLP) tasks like Named-entity recognition (NER). It is built with Python 3.*, Numpy, and Numba, ensuring efficient processing. Usage examples are provided for both multiple and single model predictions, making it accessible for developers looking to enhance their object detection pipelines.

Codic Solution is a privately owned software services company specializing in custom software development and AI integration for businesses worldwide. They offer a range of services including system design, SaaS development, AI integration, and data science. Their expertise covers areas like enterprise resource planning (ERP), customer relationship management (CRM) integration, cloud-based solutions, mobile app development, and web application development. Codic Solution focuses on delivering scalable, secure, and intuitive solutions to enhance operational efficiency, automate workflows, and drive digital transformation for their clients.

BoomPop AI is an all-in-one event management platform designed to simplify the complexities of planning group events. It brings together essential functions like vendor sourcing, guest management, AI assistance, and budgeting, eliminating the need for multiple tools. The platform automates RFPs and negotiations, saving up to 50% across 1.5 million vendors. Users can launch polished event websites, collect preferences, and send automatic updates. A built-in AI assistant provides personalized venue recommendations, planning updates, and handles guest texts. BoomPop also offers a clear view of event finances, replacing spreadsheet spirals with shareable reports. It supports various event types, including offsites, client events, and conferences, and partners with over 100 small businesses.

goHeather AI Contract Review is an AI-powered platform designed to streamline contract review processes for businesses, legal teams, and operations. It allows users to upload Word documents or PDFs for instant analysis, identifying issues based on custom playbooks or common-law standards. The tool provides clear, plain-English explanations of risks and offers suggested edits that can be applied directly. Key features include lawyer-trained AI, localization to specific jurisdictions, and the ability to train the AI with custom playbooks. It also offers a Microsoft Word Add-In for direct redlining, an AI chat for clause explanations, and features like document comparison, obligation tracking, and multi-language support. goHeather aims to help teams close deals faster by turning complex legal jargon into actionable data.

WPPConnect is an open-source project developed by the JavaScript community, designed to export functions from WhatsApp Web to Node.js. This allows developers to create a wide range of interactions, including customer service, media sending, and intelligence recognition based on artificial phrases. The tool supports essential WhatsApp functionalities such as sending various media types (text, image, video, audio, docs), managing contacts, chats, groups, and group members, and forwarding messages. It also features automatic QR refresh, multiple session support, and the ability to send stickers and location data. WPPConnect is continuously updated to adapt to changes in WhatsApp, with maintainers ensuring the core algorithm remains consistent while functions are updated.

The Surprise Trip Planner project demonstrates the application of the CrewAI framework to automate the creation of surprise travel plans. This tool orchestrates autonomous AI agents, enabling them to collaborate effectively and execute complex tasks related to travel planning. By leveraging role-playing AI agents, it aims to deliver a seamless and exciting travel experience. The project is open-source and available on GitHub, providing a practical example for developers and enthusiasts interested in building AI-powered workflows. Users can configure environment variables, install dependencies, and customize agent and task configurations to tailor the travel planning process to specific needs. It uses GPT-4 by default, requiring access to the model for execution.

Emergence AI delivers mission-critical agentic infrastructure for enterprises, specializing in verified and governed AI agents. These agents are designed to plan, reason, and act across complex systems, from semiconductor design to broader enterprise operations. The platform offers solutions built on determinism, ensuring predictable and verifiable operations; governed everywhere, with formally verified and risk-managed agent networks; and continual self-improvement through persistent memory systems. Emergence AI's solutions include Emergence Agents, Emergence Assistant, and Semantic Intelligence, with a strong focus on the semiconductor industry for design, verification, and silicon lifecycle automation. Their expertise in context management and long-term memory sets a new standard for AI memory performance.

HateToCall.com is an AI assistant service designed to eliminate the frustration and time commitment associated with customer service calls. Users simply set the phone number and goal for the call, and the AI takes over, handling tasks such as negotiating lower bills, appealing airline compensation, or canceling subscriptions. The AI can call anyone, anytime, for anything, including large companies and government entities. If extra details are needed during a call, the AI puts the call on hold and contacts the user. Once the call is complete, the AI sends a summary of the outcome, allowing users to avoid hours on hold and infinite call transfers. It offers a free first AI call to get started.

vimGPT is an innovative open-source project that enables web browsing through the combined power of GPT-4V's vision capabilities and the keyboard-centric navigation of Vimium. This tool explores how multimodal models can interact with web interfaces, addressing the challenge of determining user intent without direct access to the browser DOM. By integrating Vimium, vimGPT provides a unique method for models to interact with web elements. The project is continuously evolving, with ideas for future enhancements including the use of Assistant API for context retrieval, specialized Vimium forks for element overlay, and higher-resolution image processing for improved detection. It also aims to incorporate JSON mode for the Vision API and speech-to-text capabilities for enhanced accessibility.

Youtu-GraphRAG is a revolutionary framework designed for graph retrieval-augmented complex reasoning, offering a vertically unified agentic paradigm. It jointly connects the entire framework as an intricate integration based on graph schema, allowing seamless domain transfer with minimal intervention. The tool boasts a 33.6% lower token cost and 16.62% higher accuracy over state-of-the-art baselines, making it ideal for multi-hop reasoning, summarization, and knowledge-intensive tasks. Key innovations include schema-guided hierarchical knowledge tree construction, dually-perceived community detection, and agentic retrieval with iterative reflection. It also provides advanced construction and reasoning capabilities for real-world deployment, including user-friendly visualization and parallel sub-question processing.

ZeAI Soft is a cutting-edge product and service-based company focused on AI, Machine Learning, and Web App Development. They aim to empower businesses with smart, scalable technology, supported by partnerships with global tech leaders. The company emphasizes a customer-centric approach, working closely with clients to understand unique challenges and provide customized solutions. ZeAI Soft offers end-to-end service, handling projects from concept to execution with precision, and provides continuous support and maintenance post-delivery. They differentiate themselves through a strong emphasis on continuous improvement and innovation, ensuring their technology stays current with industry trends.

Synnada is an AI infrastructure company dedicated to rethinking how intelligent systems are built. It provides the foundational technology for data science and content understanding, enabling the creation of reliable, scalable, and agent-native systems. Built by Apache DataFusion contributors, Synnada's offerings include Mithril for efficient model compilation, Tenet for multi-cloud AI workload deployment, and Agentia, a runtime for persistent agent systems with first-class code execution. This infrastructure supports the agentic economy, allowing intelligent agents to operate continuously across clouds, datasets, and decision loops, ensuring correctness, efficiency, and long-term operability for production-grade AI.

Bridgesoft is an agricultural technology firm that integrates deep learning, image processing, embedded hardware, and edge computing into existing farming machinery. The company's primary goal is to provide high-tech solutions for efficiency and savings in pesticide and liquid fertilizer application, aiming for up to 90% reduction in chemical use. Bridgesoft's technology helps farmers reduce costs, increase profitability, and compete globally by bridging the gap between agricultural practices and advanced technology. The company develops 100% local software, AI models, and electronic hardware through its R&D team, focusing on making agricultural technology accessible to all farmers, including small-scale operations, and promoting environmentally friendly and sustainable farming practices.

AI Rock ID is an iOS application designed to identify rocks, crystals, and minerals from a single photograph. Users can simply point their iPhone camera at a specimen to receive instant identification, including its name, type, Mohs hardness, and an estimated value. The app leverages AI image recognition to compare visual features against a database of over 5000 specimen types. It offers free daily scans and does not require an account or signup, prioritizing user privacy by processing and deleting photos immediately after identification. Beyond basic identification, AI Rock ID also features a crystal encyclopedia, a personal collection tracker, and specific identification tools for various categories like gemstones, minerals, and even gold.

AppSter Solutions is a software company dedicated to transforming innovative ideas into tangible technological solutions. They specialize in comprehensive mobile solutions and software development, with a strong emphasis on creating user-centric experiences. The company leverages advanced technology, including AI, to build robust mobile applications and AI-driven platforms. Their core mission is to address real-world challenges through cutting-edge software development, ensuring that the final products are not only functional but also intuitive and impactful for users.

Arbiter is a Rust-based, event-driven multi-agent framework designed for orchestrating strongly-typed, high-performance simulations and networked systems. It provides foundational types and traits for building actor-based systems with pluggable networking and lifecycle management. Tailored for discrete-event simulation, automated trading, and complex distributed systems, Arbiter's core concepts include Actors for execution units, LifeCycle for actor behavior, Handlers for message processing, Networks for system connections, and Runtimes for managing execution context. The framework is open-source and actively developed by Harnesslabs, offering extensive documentation and examples for in-depth understanding.

Arraymancer is a powerful n-dimensional tensor (ndarray) library implemented in Nim, designed for high performance and ease of use. It provides a robust foundation for scientific computing, machine learning algorithms, and deep learning applications. The library supports various backends including CPU, Cuda, and OpenCL, and can leverage OpenMP for multithreaded compilation. Key features include basic math operations generalized to tensors, matrix algebra primitives, efficient slicing, broadcasting support, and a variety of reshaping operations. Arraymancer can handle tensors up to 6 dimensions and supports reading/writing .csv, Numpy (.npy), and HDF5 files. While its deep learning components are still evolving, it offers functionalities for neural networks, including fully-connected layers and convolutional networks, making it a versatile tool for developers and data scientists working with Nim.

Chinese-Text-Classification-Pytorch is an open-source toolkit designed for Chinese text classification tasks, built on the PyTorch framework. It offers out-of-the-box implementations of several popular text classification models, including TextCNN, TextRNN, FastText, TextRCNN, BiLSTM_Attention, DPCNN, and Transformer. The toolkit is user-friendly and ready for immediate deployment, supporting both character-level input and the integration of pre-trained word vectors, specifically using Sougou News Word+Character 300d. It also includes a pre-processed Chinese dataset (THUCNews) for training and evaluation, making it a comprehensive resource for researchers and developers working on Chinese NLP.

all-in-rag is an open-source educational resource designed for developers interested in Retrieval-Augmented Generation (RAG) technology. It offers a full-stack guide, covering RAG core concepts, data processing workflows, index building and optimization, advanced retrieval techniques, and system evaluation. The resource emphasizes hands-on practice with rich project examples, including multi-modal RAG support for text and image retrieval. It aims to provide a systematic learning path for building production-ready intelligent Q&A and knowledge retrieval systems, addressing the fragmented nature of existing RAG tutorials. The project is suitable for developers with Python programming skills and an interest in AI engineering.