agent

imini AI is a super AI agent that integrates the latest large AI models such as GPT-5, Grok 4, Gemini 2.5 Pro, Claude Opus 4 Thinking, and DeepSeek R1. It has excellent intelligent interaction functions and provides users with efficient chat, in-depth research, report writing and other services. Positioned to improve users’ work and life efficiency.

CatDoes is a no-code AI mobile app builder that enables anyone to build mobile apps for their business and personal use. It uses a multi-agent approach to build mobile applications through natural language descriptions, requiring no technical skills.

Deforge is an AI agent building tool that helps users create, connect and deploy AI agents through an intuitive node-based interface, from simple automation to blockchain integration, without writing any code. Its main advantages lie in its user-friendly interface, simplified AI agent construction process, and reduced technical threshold.

Omnara is an AI agent command center that can monitor, manage and collaborate on an entire AI agent fleet. Its main advantage is that it can monitor, debug and guide AI agents in real time, so that users are not restricted to their desks. Omnara’s background includes a team of engineers from well-known companies and Y Combinator support.

MuleRun is an AI agent marketplace where users can find and run problem-solving AI agents. This product provides a quick and easy solution to help users automate tasks.

Muka is an AI agent tool that helps users complete digital tasks. Users can deploy intelligent AI agents called Spirits to perform various tasks, connect various tools, and provide convenient workflows.

xpander.ai is a platform that can deploy AI agents in Slack without the need for infrastructure. It has autonomous memory, network search and code interpreter functions, which can save LLM costs and implement Slack OAuth integration, making it suitable for various work scenarios.

Second Me is an open source prototype designed to allow users to create their own AI selves, retain personal characteristics, and expand themselves in the digital world. It uses hierarchical memory modeling and user alignment algorithms to ensure user data is stored locally and completely private. This form of AI not only helps users manage information, but also interacts with other AI in a global network, promoting creativity and collaboration. The main advantage of Second Me is that it protects users' privacy and allows users to truly control their digital identity. It is suitable for technology enthusiasts, AI experts and professionals in various fields. This product is currently under development and users can get the latest version on GitHub.

OpenManus is an open source intelligent agent project that aims to implement functions similar to Manus through open source, but can be used without an invitation code. The project was jointly developed by multiple developers and is based on a powerful language model and flexible plug-in system, which can quickly implement various complex tasks. The main advantages of OpenManus are that it is open source, free and easy to extend, making it suitable for developers and researchers for secondary development and research. The project background stems from the need to improve existing intelligent agent tools, with the goal of creating a fully open and easy-to-use intelligent agent platform.

Helix is ​​an innovative vision-speech-action model designed for universal control of humanoid robots. It solves several long-term challenges for robots in complex environments by combining visual perception, language understanding and motion control. The main advantages of Helix include strong generalization capabilities, efficient data utilization, and a single neural network architecture that does not require task-specific fine-tuning. The model aims to provide robots in home environments with on-the-fly behavior generation capabilities, allowing them to handle never-before-seen items. The emergence of Helix marks an important step in adapting robotics technology to daily life scenarios.

AgentSociety is an advanced framework developed by Tsinghua University's FIB Laboratory, designed to simulate human behavior and social interaction through LLM-driven agents. It leverages the planning, memory, and reasoning capabilities of large language models (LLMs) to generate realistic behavioral patterns and supports environment design based on data sets, text, and rules. This framework is of great significance in the fields of social science research, urban planning, and education, and can help researchers better understand human behavior and social dynamics.

Tbox is a large-model technology product based on Alipay's life scenarios. It is designed to quickly build professional-level intelligence for enterprises and help business growth. It integrates advanced technologies such as Ant Bailing Large Model, Ant Tianjian, and Lingjing Digital Human, and can realize functions such as experience upgrades and intelligent decision-making. Tbox is suitable for a variety of industries, such as people's livelihood, government affairs, travel, scenic spots, medical care, etc., and improves user experience and business efficiency through intelligent services. Its price and specific positioning vary according to the needs of the enterprise, providing customized solutions for enterprises.

Magma is a multi-modal basic model launched by the Microsoft research team, aiming to achieve the planning and execution of complex tasks through the combination of vision, language and movement. Through large-scale visual language data pre-training, it has the capabilities of language understanding, spatial intelligence and action planning, and can perform well in tasks such as UI navigation and robot operation. The emergence of this model provides a powerful basic framework for multi-modal AI agent tasks and has broad application prospects.

kimi-latest is the latest AI model launched by Dark Side of the Moon. It is upgraded simultaneously with Kimi smart assistant. It has powerful context processing capabilities and automatic caching capabilities, which can effectively reduce usage costs. The model supports image understanding and multiple functions such as ToolCalls and network search, making it suitable for building AI intelligent assistants or customer service systems. Its price is 1 yuan per million Tokens and is positioned as an efficient and flexible AI model solution.

OmAgent is a multi-modal native agent framework for smart devices and more. It uses a divide-and-conquer algorithm to efficiently solve complex tasks, can pre-process long videos and conduct questions and answers with human-like accuracy, and can also provide personalized clothing suggestions based on user requests and optional weather conditions. At present, the price is not clearly displayed on the official website, but from a functional point of view, it is mainly targeted at user groups that require efficient task processing and intelligent interaction, such as developers, enterprises, etc.

Gemini 2.0 Flash Experimental is the latest AI model developed by Google DeepMind, designed to provide an intelligent agent experience with low latency and enhanced performance. This model supports the use of native tools and can natively create images and generate speech for the first time, representing an important advancement in AI technology in understanding and generating multimedia content. The Gemini Flash model family has become one of the key technologies that promotes the development of the AI ​​field with its efficient processing capabilities and wide range of application scenarios.

Cosmos is an AI operating system developed by Humane, built for the universe of connected devices. It provides personalized assistance by understanding user preferences and needs, simplifying interactions and handling complex tasks across all devices. The core of Cosmos is Ai Bus, a powerful AI coordination system that seamlessly coordinates various AI models, data sets, services and device capabilities to provide a smooth and intuitive experience. CosmoOS supports multiple device forms and adapts to the latest AI technology development, making it easy to add new agents and capabilities. It also emphasizes data privacy and ownership, placing control firmly in the hands of individuals and organizations.

Agent S is an open agent framework designed to enable autonomous interaction with computers through a graphical user interface (GUI), transforming human-computer interaction by automating complex multi-step tasks. It introduces an experience-enhanced hierarchical planning method that utilizes online network knowledge and narrative memory to extract high-level experience from past interactions, decompose complex tasks into manageable subtasks, and use episodic memory for step-by-step guidance. Agent S continuously optimizes its actions and learns from experience to achieve adaptable and effective task planning. Agent S outperformed the baseline's 9.37% success rate on the OSWorld benchmark (a relative improvement of 83.6%) and demonstrated broad generality on the WindowsAgentArena benchmark.

π0 is a universal robot basic model designed to allow AI systems to acquire physical intelligence through physical training and be able to perform various tasks, just like large language models and chatbot assistants. π0 acquires physical intelligence through physical experience trained on robots, can directly output low-level motor commands, control a variety of different robots, and can be fine-tuned for specific application scenarios. The development of π0 represents an important advance in the application of artificial intelligence to the physical world, by combining large-scale multi-task and multi-robot data collection with new network architectures to provide the most capable and dexterous general-purpose robotic policy to date.

Computer use is a new feature of Claude 3.5 Sonnet, an AI model launched by Anthropic. It can simulate the interaction between humans and computers, performing operations such as clicking on the screen and inputting information. The development of this feature represents a significant progress in AI's ability to simulate human behavior, unlocking a wide range of application scenarios for AI assistants. The Computer use function has been significantly improved in terms of security, multi-modal capabilities and logical reasoning, representing a new frontier of AI technology. Currently, this feature is in the public beta stage, and its performance is in a leading position among similar AI models.

AiAlly AI Employee is a revolutionary artificial intelligence employee platform that helps enterprises achieve true collaboration and greatly improve productivity by simulating the thinking, learning and evolving abilities of real employees. The product provides enterprises with a new way of working through autonomous problem solving, seamless AI teamwork, customizable AI personalities, and enterprise-grade security measures. AiAlly AI Employee can complete complex tasks independently, improve decision-making capabilities, and work seamlessly with human teams while protecting the security of enterprise and user data.

AI Smart Link is a wearable device jointly developed by Sharp Corporation and Kyoto University of the Arts to enable natural communication with generated AI. The device captures the user's environment through built-in microphones and cameras and responds through voice, supporting users' applications in a variety of life scenarios, such as cycling navigation, cooking guidance and AIoT home appliance operation. The device is equipped with edge AI technology 'CE-LLM' developed by Sharp, which can quickly respond to user needs and achieve a smooth and natural conversation experience.

Phoenix™ is the first general-purpose humanoid robot powered by the Carbon™ AI control system, designed specifically for work. It was named one of the best inventions of 2023 by Time magazine. Sanctuary technology helps people work more safely, efficiently, and sustainably through remotely controlled or supervised universal robots, while creating new job opportunities, solving the global labor shortage, and bringing new hope and opportunities to those with limited physical abilities.

The S1 robot developed by Astribot is a new generation of AI robot that can imitate learning and perform multiple complex tasks that are useful to humans. The design concept of S1 robot is to allow billions of people to have AI robot assistants to help people complete boring, difficult or dangerous tasks. The product has passed large-scale model testing and is expected to be commercialized in 2024.

DuerOS X is the world's first AI native operating system launched by Xiaodu based on the Baidu Wenxin model. It completely subverts the traditional model of people adapting to the system, realizes the end-to-end connection of users' intentions and tasks, and greatly expands the boundaries of the operating system. DuerOS The storage, retrieval and understanding capabilities of personalized long and short memory enable DuerOS X to remember historical content and user personalized preferences more clearly. In addition, the application of multi-modal perception technology allows DuerOS

Using BrainSoup, you can create custom AI agents to handle tasks and automate processes through natural language. Increase the power of AI with your data while maintaining optimal privacy and security. BrainSoup supports multiple large-scale language models and semantic core technologies to make AI agents more powerful and personalized.

Tab is a wearable artificial intelligence device that integrates voice assistant, real-time translation, schedule management and other functions, and can become the user's smart companion. It adopts a thin and portable design and is comfortable to wear. Through voice interaction, it can help users improve work efficiency and accompany users in their daily lives.

Homeway is a platform that provides free, private, and secure remote access to Home Assistant. It also supports integration with Alexa and Google Assistant, and offers the official Home Assistant remote access app for iOS and Android. Homeway allows users to remotely control and manage their Home Assistant smart home system anytime, anywhere.