AI Agents & Automation

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.

Agent Squad is a flexible, lightweight, and open-source framework designed for orchestrating multiple AI agents to handle complex conversations. It features intelligent intent classification to dynamically route queries to the most suitable agent based on context, and offers dual language support with full implementations in both Python and TypeScript. The framework supports flexible agent responses, including streaming and non-streaming, and provides robust context management to maintain coherent interactions across agents. Its extensible architecture allows for easy integration of new agents or customization of existing ones, and it can be universally deployed across various platforms like AWS Lambda or local environments. Agent Squad also includes pre-built agents and classifiers, along with a new SupervisorAgent for sophisticated team coordination and parallel processing of tasks.

Uni The Present is a premium, production-ready LMS UI starter for Next.js App Router, specifically designed for recorded courses and AI tutoring. It offers comprehensive student and instructor flows, including a student dashboard, a course viewer with video, syllabus, and notes, an AI tutor chat shell, assignments overview, messaging inbox, and a notes workspace. Instructors benefit from profiles and a studio with a grading queue. Built with Tailwind CSS 4, shadcn/ui, Framer Motion, and a Feature-Sliced architecture, it allows for easy integration with real APIs like Supabase, Postgres, and Stripe. The starter kit also includes a dedicated style guide and pre-configured metadata for quick rebranding and launch.

pi-mono is an extensive AI agent toolkit designed for developers to build and manage AI agents effectively. It features a coding agent CLI for interactive development, a unified multi-provider LLM API supporting platforms like OpenAI, Anthropic, and Google, and libraries for creating both Terminal User Interfaces (TUI) and web-based AI chat interfaces. The toolkit also includes a Slack bot for delegating messages to the coding agent and a CLI for managing vLLM deployments on GPU pods. It emphasizes sharing open-source coding agent sessions to improve agent performance through real-world tasks and failures.

CVEDIA provides an AI video analytics platform built for edge deployments and proven in defense applications. It offers solutions for security, business intelligence, and critical infrastructure, enabling real-time threat detection, perimeter security, and incident response. The platform transforms raw video into metadata for business intelligence, including counting dashboards and customer flow analysis. CVEDIA differentiates itself by owning the full AI pipeline, from synthetic data generation and model training to hardware optimization and VMS integration. It supports various hardware architectures and offers native plugins for leading VMS platforms like Milestone XProtect and Nx Witness, ensuring deployment flexibility and efficiency.

Gradio User History is a plugin designed to cache generated images for users within Hugging Face Spaces. This tool aims to improve the user experience by allowing the storage and retrieval of previously generated images, which can be particularly useful for applications involving iterative image generation or for users who frequently revisit their past creations. The plugin requires users to sign in with Hugging Face to access its functionality, ensuring a personalized and secure experience. While the current live website content indicates a runtime error, the intended purpose is to provide a seamless way for users to manage and access their image generation history within Gradio applications hosted on Hugging Face Spaces.

InnerEye offers solutions to supercharge complex decision-making by integrating human intelligence with artificial intelligence, creating what they call "Minded A.I." The platform aims to accelerate the journey to AI applicability, reliability, and business value by enabling AI models to learn faster, be more accurate, and drive smarter decisions. InnerEye achieves this by leveraging neuro-technology and brain-computer interfaces to understand human experts' capabilities, transferring their knowledge to AI models. This fusion of human and artificial intelligence, along with relevant data, optimizes complex decisions. InnerEye provides solutions like Sense.I for optimizing AI training and decision-making with higher accuracy and faster learning, and Sense Plus for assessing and enhancing experts' skills to create a "minded organization."

SepLLM is a plug-and-play framework designed to accelerate large language models (LLMs) by addressing their computational demands and inference speed challenges. It leverages a key observation that certain separator tokens, like punctuation, disproportionately contribute to attention scores. SepLLM condenses information from segments between these separators into the separator tokens themselves, effectively compressing segments and eliminating redundant tokens without significant information loss. The framework also includes efficient kernels for training acceleration. Experimental results demonstrate its effectiveness across training-free, training-from-scratch, and post-training settings. For instance, using a Llama-3-8B backbone, SepLLM achieves over a 50% reduction in KV cache on the GSM8K-CoT benchmark while maintaining comparable performance. In streaming settings, it can process sequences of up to 4 million tokens or more, ensuring consistent language modeling capabilities. SepLLM also provides SepCache, a portable and efficient Cache class available on HuggingFace, supporting Llama 3.1 series and newer transformers.

Sonnet is a powerful open-source library built on top of TensorFlow 2, specifically designed by DeepMind researchers to provide simple, composable abstractions for machine learning research. It facilitates the construction of neural networks for various purposes, including supervised learning, unsupervised learning, and reinforcement learning. The library centers around the `snt.Module` concept, allowing users to define custom modules or utilize many predefined ones like `snt.Linear` and `snt.Conv2D`. Sonnet is unopinionated about training frameworks, encouraging users to build their own or adopt existing ones. It emphasizes clarity and focus in its codebase, making it easy to understand and extend. Key features include support for TensorFlow checkpointing and saved models, enabling robust serialization and deployment of models.

sqlite-vec is an extremely small, yet powerful, vector search SQLite extension designed for broad compatibility. It allows users to store and query various vector types, including float, int8, and binary, within vec0 virtual tables. Developed in pure C with no external dependencies, sqlite-vec boasts exceptional portability, running seamlessly across diverse environments such as Linux, MacOS, Windows, in-browser with WASM, and on Raspberry Pis. It supports storing non-vector data in metadata, auxiliary, or partition key columns, making it a versatile solution for integrating vector search capabilities directly into SQLite databases.

The RoboCup Federation is an international scientific initiative dedicated to advancing the state of the art in intelligent robots and artificial intelligence. Established in 1997, its original mission was to develop a team of robots capable of defeating human soccer champions by 2050. The federation organizes various competitive leagues, including RoboCupSoccer, RoboCupRescue, RoboCup@Home, RoboCupIndustrial, and RoboCupJunior, fostering research and development in diverse robotic applications. Beyond competitions, RoboCup hosts symposiums, publishes research papers, and offers awards to recognize significant contributions to the field. It serves as a platform for international collaboration, bringing together researchers, students, and enthusiasts to push the boundaries of robotics and AI.

Skild AI is dedicated to developing general-purpose robotic intelligence, aiming to bridge the gap between AI in cyberspace and its application in the physical world. The company's core thesis is to create an "omni-bodied brain" capable of controlling any robot for any task, overcoming limitations of specific robot or task types. Skild AI achieves this by learning from human videos, offering a scalable solution to the robotics data problem. Their technology is applied in various real-world scenarios, including security and inspection robots for navigating unstructured environments, mobile manipulation platforms for tasks like grasping and navigation, and autonomous packing for precise and dexterous skills. This allows users to build applications via an API without delving into the complexities of the physical world.

Quantum Elements offers an AI-native quantum development platform designed to accelerate the building, optimization, and launching of quantum applications. The platform integrates AI-powered quantum simulation, automated calibration, and circuit optimization to enhance the development process. Key features include a noise-aware quantum simulation environment, an AI-powered quantum assistant, and real-time error suppression, making it suitable for both researchers and engineers. It supports hardware-agnostic execution, providing flexibility for various quantum computing environments. The platform aims to simplify complex quantum development tasks, allowing users to focus on innovation rather than intricate technical challenges.

Quantum Intelligence provides advanced AI and data science solutions tailored for enterprise needs. Their offerings include comprehensive machine learning operations (MLOps), enterprise analytics, and AI consulting services. The company specializes in deploying AI solutions for business analytics and offers quantum-powered analytics and automation tools. Based in Dar es Salaam, Tanzania, Quantum Intelligence aims to address challenges in AI adoption within the African market, focusing on building robust AI systems and providing strategic insights through data science.

Meta AI Demos is a platform designed to provide users with direct access to experimental AI demonstrations and research developed by Meta. It serves as a showcase for the company's latest advancements in artificial intelligence, allowing individuals to interact with and explore various AI models and applications. The platform is ideal for AI researchers, developers, and technology enthusiasts who wish to understand the practical capabilities and potential of new AI technologies. By offering hands-on experiences, Meta AI Demos facilitates learning and exploration of the evolving AI landscape, directly from one of the leading research institutions.

spark-deep-learning provides Deep Learning Pipelines for Apache Spark, focusing on distributed deep learning training jobs using Horovod. While the open-source version primarily supports local development, it integrates seamlessly with Databricks Runtime for Machine Learning to launch Horovod jobs as distributed Spark jobs. This allows data scientists and engineers to manage cluster setup and scale their deep learning models efficiently. The library offers functionalities for running training code across multiple processes, with options to specify the number of parallel processes for optimal resource utilization on GPU or CPU clusters. It simplifies the deployment and execution of complex deep learning tasks within the Spark ecosystem.

Evo AI is an open-source platform designed for the creation and management of AI agents, offering robust integration with diverse AI models and services. It provides a comprehensive suite of features including client management, MCP server configuration, and custom tool management. The platform supports multiple agent types such as LLM, A2A, Sequential, Parallel, Loop, Workflow, and Task agents, allowing for flexible and complex agent development. Key technologies include FastAPI for the backend, Next.js for the frontend, and PostgreSQL for the database. It also integrates with Langfuse for detailed tracing and observability of agent executions, and implements Google's Agent 2 Agent (A2A) protocol for seamless interoperability. Evo AI is ideal for developers looking to build, deploy, and manage sophisticated AI agent systems.

Wavestone, formerly qdive, is a leading management and technology consulting firm specializing in strategic transformations. They provide a comprehensive portfolio of high-impact consulting services, blending deep industry expertise with advanced technology and cross-functional capabilities. Their offerings include Artificial Intelligence & Data, Cybersecurity, IT Strategy & CTO Advisory, SAP Consulting, and Software & Application Development & Integration. Wavestone also focuses on business strategy, compliance, risk, customer experience, and sustainability. With over 6,000 employees across 17 countries, they support clients worldwide in redesigning business models and implementing cutting-edge technologies, aiming to drive positive impact and sustainable transitions.

Sacher AI specializes in designing, evaluating, and delivering human-facing AI systems for healthcare and behavior change. The platform assists digital health teams in creating AI solutions that enhance patient experience, optimize workflows, and perform effectively in real-world settings. Sacher AI offers services ranging from strategic AI discovery and governance frameworks to AI product build and delivery, grounded in behavioral science. Key offerings include PromptSafe for persona-based simulation testing of AI agents and OVRSI for independent post-deployment monitoring of user-facing AI, ensuring safety and clinical appropriateness from the outset. They are trusted by GLP-1 platforms and global weight management brands.

Red Marble AI is an Australian artificial intelligence software development and strategy company, specializing in helping businesses leverage AI for competitive advantage. With a decade of expertise, they have delivered over 100 AI-driven projects across diverse sectors including construction, education, technology, and mining. Their services encompass AI strategy and governance, AI engineering, and AI education. They offer rapid prototyping, AI product engineering, and AI Ops for continuous improvement. Red Marble AI also provides comprehensive governance frameworks and compliance strategies, partnering with 2021.AI for enterprise-wide AI model visibility and automated legal compliance. They aim to deliver value within weeks and are backed by a strategic investment from Centerstone Capital.

Flow AI offers a robust infrastructure layer designed to transform analytical SaaS products into intelligent, agentic systems. It provides a schema-aware data model, deterministic reasoning, and validated generative UI components, allowing businesses to ship reliable analytical agents directly into their product UI. The platform addresses challenges like complex data schemas and domain logic, enabling agents to natively reason over structured data, rules, and customer context. Flow AI supports multi-step data operations, transparent reasoning plans, and generates interactive visual insights that fit natively into existing UI, ensuring enterprise-safe execution and scalability for data-heavy workloads.

Swiss Engineering Partners AG (SwissEP) specializes in bringing advanced AI solutions into industrial processes, focusing on custom vision solutions, machine learning, and automation to significantly enhance efficiency and scalability. They rapidly implement AI to drive business forward, offering services like autonomous testing to increase throughput without system duplication, and AI visual inspection for consistent and precise defect detection. SwissEP provides intelligent solutions such as process automation, cobot integration for seamless human-robot collaboration, custom AI tailored for complex data challenges, and computer vision for reliable visual inspections and classification. Their approach emphasizes Swiss precision, rapid development, and scalable, customizable systems.

Hopx offers secure, isolated sandboxes for executing untrusted code, specifically designed for AI agents and autonomous systems. It leverages Linux micro-VMs that launch in approximately 100ms, providing hardware-level security and kernel isolation superior to containers. Users can run Python, JavaScript, Bash, and Go code with real-time streaming output, background execution, and full filesystem operations. Hopx supports various use cases including validating AI-generated code, running long-running jobs, CI/CD testing, data processing, and even desktop automation. The platform provides a simple SDK for integration and an MCP server for IDEs, ensuring code execution is safe, fast, and scalable.

Wirestock serves as a bridge between creative professionals and AI development teams, offering a platform for sourcing high-quality, ethically obtained multimodal data. Creators can find freelance projects in photography, videography, illustration, and graphic design, earning income by contributing content. For AI Labs, Wirestock provides access to a vast library of over 50 million pieces of content, including images, video, and vector art, all cleared for AI training. The platform emphasizes thoughtful QA and review to ensure data quality and offers customized datasets tailored to specific AI model needs, ensuring legal protection and peace of mind for AI developers.