AI Agents & Automation

agents-starter is a comprehensive starter kit designed for developers to build AI chat agents on Cloudflare's platform. Leveraging the Agents SDK and Workers AI, it provides a robust foundation for creating intelligent agents without requiring an API key for Workers AI. The kit includes pre-built tools for common functionalities such as weather information, timezone detection, calculations with human approval, and task scheduling. It also supports vision capabilities for image understanding and offers features like streaming responses, real-time WebSocket connections, and message persistence. Developers can easily customize agents by changing system prompts, replacing demo tools with real API calls, and adding new server-side, client-side, or approval-based tools. The project structure is well-defined, making it straightforward to extend and deploy agents on Cloudflare's global network.

Invoce.ai is an AI-powered invoice generator designed for freelancers and small businesses, simplifying the process of creating and managing invoices. The tool features an intuitive chat interface, enabling users to generate professional invoices rapidly and efficiently. Beyond invoice creation, Invoce.ai supports the generation of payment links, streamlining the payment collection process. It also provides a centralized platform for managing clients, tracking invoices, and monitoring payments, aiming to consolidate essential financial tasks into one accessible solution. This makes it easier for users to maintain organized financial records and ensure timely payments.

OctoTools is an open-source, training-free, and easily extensible agentic framework designed to tackle complex reasoning across diverse domains. It introduces standardized tool cards to encapsulate tool functionality, a planner for both high-level and low-level planning, and an executor to carry out tool usage. The framework enables training-free integration of new tools without additional training or refinement. OctoTools supports a wide array of LLM engines, including OpenAI, Azure OpenAI, Anthropic, TogetherAI, DeepSeek, Gemini, Grok, vLLM, LiteLLM, Forge, and Ollama. It has demonstrated substantial accuracy gains over other frameworks in various complex reasoning tasks.

ArXivChatGuru is an open-source Streamlit application designed to facilitate interaction with research papers from arXiv. It functions by allowing users to specify a topic and the number of papers to load. The app then retrieves these papers, splits them into manageable chunks, and generates OpenAI embeddings for each chunk. These chunks and embeddings are stored in a topic-scoped Redis vector index, which also acts as a semantic cache. Utilizing LangChain, the tool retrieves the most relevant chunks for user questions, providing context to a chat model for grounded Q&A. This project is intentionally simple, serving as a valuable learning resource for understanding Retrieval Augmented Generation (RAG) workflows in an academic context, rather than a production-ready research assistant.

LEVELS OS is an AI-powered software designed to automate document verification processes on construction sites. It acts as a digital operator, analyzing, verifying, and organizing all supplier documentation, including ITP, worker, and vehicle-related documents, in minutes. The platform supports various document formats and automatically extracts relevant information, checks for compliance, deadlines, and completeness against current regulations. LEVELS OS provides a centralized dashboard for monitoring supplier status, documents, and deadlines, and generates professional reports. It also sends automatic notifications for critical document expirations, anomalies, or missing files, helping to prevent site blockages and ensure continuous regulatory compliance. This solution significantly reduces the time spent on manual checks and minimizes human error.

azure-openai-proxy is an open-source tool designed to seamlessly convert official OpenAI API requests into Azure OpenAI API requests. This proxy eliminates the differences between the two platforms, allowing the OpenAI ecosystem to access Azure OpenAI services with zero integration cost. It supports a wide range of models, including GPT-4 and Embeddings, and is compatible with popular frameworks like Langchain. Developers can easily deploy and configure the proxy using Docker, with options for environment variables or a configuration file to manage endpoints, API keys, and model mappings. This makes it an invaluable adapter for developers looking to leverage Azure's infrastructure while maintaining compatibility with existing OpenAI-based applications.

Muddy is a multiplayer browser specifically built for ambitious teams to enhance collaboration and productivity. It eliminates tab clutter by intelligently organizing and categorizing applications, messaging, and web content. Users can create shared views with their favorite apps, enabling seamless co-design and co-working experiences. Muddy's AI learns from app usage and conversations to answer complex questions, acting like an intelligent coworker. Key features include universal commenting across all web apps, infinite rewind functionality to review past work and conversations, and real-time team presence. It supports all browser-compatible apps and Chrome extensions, optimizing memory and battery life by hibernating inactive tabs.

KS Smart Solutions, incorporated in 2016, offers bleeding-edge automated solutions tailored to client needs across diverse industries. They focus on digital transformation through Industry 4.0, AI, automation, and cloud technologies. Their expertise spans VR/AR solutions, Machine Learning/AI, web/mobile app development, and enterprise solutions. KS Smart Solutions aims to help clients achieve their digital objectives by developing customized IT solutions, enhancing agility, productivity, quality, and sustainability. They serve sectors like manufacturing, smart cities, defense, education, dairy, and entertainment, providing innovative solutions from immersive VR simulations for training to integrated inventory management systems.

XAPP AI offers AI agents designed to convert demand into new business and actionable intelligence for multi-location businesses. These agents operate 24/7 across various channels, including Google Search & Maps, social media, directories, and websites, to engage customers, capture leads, and book appointments. The platform streamlines the booking process, allowing customers to describe their issue, provide contact info, and pick a preferred time. XAPP AI also collects rich first-party data from every interaction, which can be used to optimize staffing, build predictable revenue, and maximize SEO/SEM efforts. It integrates with CRMs, scheduling, and field management software, and is an approved Google Partner for enabling 'Book Online' buttons.

AI Manus is a comprehensive AI Agent system designed for general-purpose applications, enabling users to run various tools and operations within a secure sandbox environment. A key differentiator is its integration with Claw, an OpenClaw AI assistant that provides one-click deployment, isolated containers for each user, and seamless chat history management. The system supports essential tools like Terminal, Browser, File, and Web Search, with real-time viewing and takeover capabilities. Each task is allocated a separate sandbox running in a local Docker environment, ensuring isolation and security. Session history is managed via MongoDB/Redis, supporting background tasks, and conversations allow for stopping, interrupting, and file uploads/downloads. It also offers multilingual support and user authentication.

tf-encrypted is an open-source framework designed to bring privacy-preserving machine learning to TensorFlow. It allows developers to perform training and prediction on encrypted data by leveraging secure multi-party computation and homomorphic encryption. The framework aims to simplify privacy-preserving ML, removing the need for deep expertise in cryptography, distributed systems, or high-performance computing. It integrates with TensorFlow 2, supporting eager execution for easier development, and also allows for implicit graph building with `tfe.function` to maintain performance. tf-encrypted provides examples and documentation to help users get started with secure matrix multiplication, neural network inference, and training on encrypted data, showcasing its capabilities with benchmarks for various models and protocols.

Squid AI is an enterprise-grade agentic process automation platform designed to automate high-impact back-office workflows. It enables organizations to achieve faster decisions, lower operational costs, and significant return on investment. The platform offers domain-specific solutions trusted by global leaders, focusing on security, governance, and performance for mission-critical workflows. Squid AI provides agentic automation for customer support, sales operations, and financial operations, delivering benefits such as faster issue handling, reduced support costs, increased AE productivity, and quicker time-to-market for financial processes. It integrates across existing systems to automate resolutions, triage tickets, and self-heal over time, improving accuracy, speed, and customer satisfaction.

Q.ANT is at the forefront of photonic computing, offering solutions for more energy-efficient AI and High-Performance Computing (HPC). Their flagship product, the Native Processing Server (NPS), is the first commercial photonic processor designed to integrate seamlessly into existing computing ecosystems. This technology promises up to 30 times higher energy efficiency compared to conventional CMOS technologies, significantly reducing operational costs and environmental impact for data centers. Q.ANT's approach addresses the limitations of traditional computing by providing a scalable and sustainable alternative for complex AI training, inference, machine learning, physics simulations, and time-series analysis.

DistillKit is an open-source toolkit designed for the knowledge distillation of large language models (LLMs). It offers flexible and production-ready solutions for both online and offline distillation workflows, including advanced logit compression techniques. The toolkit is battle-tested, powering the training of Arcee's popular open-source models like Virtuoso, SuperNova Medius, and Blitz. Key features include real-time teacher inference for online distillation, training from pre-captured teacher outputs with compression for offline distillation, and novel polynomial approximation, quantization, and bit-packing for logit compression. It also provides flexible loss functions, sparse and dense distribution support, and HuggingFace integration, making it a robust solution for LLM optimization.

AI00 RWKV Server is an inference API server for the RWKV language model, built upon the web-rwkv inference engine. It offers high performance and accuracy, supporting Vulkan inference acceleration which allows GPU acceleration without the need for CUDA, making it compatible with AMD cards, integrated graphics, and any GPU that supports Vulkan. The server is compact and ready to use out of the box, eliminating the need for bulky PyTorch or CUDA runtime environments. It is fully compatible with OpenAI's ChatGPT API interface, 100% open source, and commercially usable under the MIT license. This makes it an excellent choice for various tasks including chatbots, text generation, translation, and Q&A, providing a fast, efficient, and easy-to-use LLM API server.

Magictool AI Chrome Extension is an all-in-one AI productivity copilot, integrating ChatGPT and 20 AI features for enhanced efficiency. It provides an AI Writing Copilot for crafting engaging content, grammar checks, text improvement, and summarization. Users can also summarize YouTube videos, chat with and summarize PDFs, and generate AI images using Stable Diffusion. The extension includes data scraping, a Magic Editor for AI-powered text editing, and a Reader Mode for clutter-free web page viewing. Additional features like Dark Mode, data analytics for CSV/Excel, custom AI commands, and note-taking further boost productivity.

opendr is a comprehensive, open-source toolkit designed to empower robotic systems with advanced perception and cognition through deep learning. It offers a modular and non-proprietary framework, making it suitable for various robotic applications in healthcare, agri-food, and agile production. The toolkit provides interfaces for Python, ROS1, ROS2, and C API, allowing developers to link robotics applications with deep learning frameworks like PyTorch and TensorFlow. OpenDR focuses on enabling robots to interact with environments, learn, categorize, make decisions, and derive knowledge, fostering cooperative human-robot interaction and cognitive mechatronics. It supports industry standards like ONNX and OpenAI Gym Interface, and integrates with Webots Open Source Robot Simulator.

DreamyBot AI is a conversational AI dream interpreter designed to provide instant and in-depth analysis of users' dreams. It helps individuals explore the subconscious beliefs and narratives that influence their daily lives, fostering personal growth and improved self-awareness. The platform offers features like a personal dream log, discussion management, memory recall for past dreams and conversations, and a personal dream dictionary to track unique symbol meanings. Available as a web application and mobile app, DreamyBot aims to make dream analysis an accessible practice for self-discovery. While offering a free tier, a Pro subscription unlocks advanced features for those seeking a deeper commitment to understanding their dreams.

IntelliMuse is an advanced AI companion platform that enables users to design and interact with personalized AI characters, referred to as Muses. Users can choose from pre-designed Muses with distinct personalities and expertise or create their own, defining traits, areas of expertise, personality, and even ethnicity and accents. The platform supports realistic voice chats via its iPhone app and text dialogues on other platforms, storing conversations for private review. IntelliMuse leverages GPT4o for its language model, aiming to integrate its voice update soon. It's designed for personal growth, research, and engaging in intelligent conversations, offering a unique blend of customization and realistic interaction.

Dog-GPT: AI Bark Translator, also known as BarkOnTrack, is an iOS mobile application designed to streamline the business operations of pet professionals. It offers features for quick scheduling, managing client and pet profiles, generating walk report cards, and GPS tracking during walks. The app also supports offline mode and allows for an unlimited number of clients, making it a robust solution for pet walkers and sitters. BarkOnTrack is part of a suite of accessible iOS apps developed by Tylor Mayfield, focusing on thoughtful UX and WCAG-focused design.

MyAIBae offers a unique platform for users to interact with AI-generated virtual companions, known as AI baes. The tool includes a "Slutometer" feature, a parody personality scanner that analyzes a selfie to provide a "slut DNA score" and matches users with an AI bae calibrated to their vibe. Users can browse a catalog of over 700 AI baes, each with distinct personalities, looks, and content. The platform emphasizes privacy, offering free previews of content and allowing users to unlock exclusive content through simple offers rather than traditional subscriptions. AI girlfriends remember conversations, adapt to communication styles, and provide a constant, judgment-free connection.

Ratham is India's leading AI-powered employee transportation management service provider, offering a comprehensive platform to automate and streamline corporate commutes. The platform, Ratham Orbit, uses AI to build routes based on live traffic and shift schedules, predicting risks and ensuring compliance. Ratham MoveX provides a flexible fleet network including sedans, SUVs, shuttles, and EVs across major Indian cities, integrated for seamless dispatching and SLA enforcement. Ratham Ops offers a trained operations team that monitors live trips, handles driver delays, and resolves issues to maintain uptime. The platform helps enterprises reduce transport costs, improve efficiency, and enhance employee safety and satisfaction.

TidyBot is a research project focused on personalized robot assistance, specifically for household cleanup tasks, leveraging Large Language Models (LLMs). The system allows robots to learn individual user preferences for object placement from a small number of examples, adapting quickly to new scenarios. It combines language-based planning and perception with the few-shot summarization capabilities of LLMs to infer generalized user preferences. The project demonstrates its approach on a real-world mobile manipulator, achieving high accuracy in putting away unseen objects. The codebase includes server and robot components, along with a benchmark dataset for evaluation, offering both teleoperation and fully autonomous modes.

Deep Vision AI, acquired by DFW Capital and now operating under EPIC iO, provides advanced AIoT solutions tailored for critical infrastructure. The platform, including DeepVision™ as a centralized VMS & Unified Command Center, offers real-time analytics, robust wireless connectivity, and AI-driven insights to significantly enhance safety, operational efficiency, and decision-making. It supports diverse applications such as physical site security with features like perimeter security and license plate recognition, and site safety with PPE validation and fire monitoring. The system also includes environmental and equipment monitoring, leveraging AI-powered sensor intelligence. EPIC iO's solutions are designed for rapid deployment and offer secure, fast, and unbreakable 4G/5G wireless connectivity, making them ideal for distributed, remote, and high-risk environments across numerous industries.