Agent S2
Agent S2 is an open, modular, and scalable framework for computer-use agents developed by Simular. These autonomous AI agents interact directly with graphical user interfaces (GUIs) on desktops, mobile devices, browsers, and various software applications, mimicking human-like control via mouse and keyboard. Building upon the initial Agent S framework, Agent S2 enhances performance and modularity by integrating both frontier foundation models and specialized models. It achieves state-of-the-art results, notably surpassing previous benchmarks on OSWorld and AndroidWorld evaluations. Key design principles include proactive hierarchical planning, where the agent dynamically updates its plans after each subtask; visual grounding for precise GUI interaction using raw screenshots; an improved Agent-Computer Interface (ACI) that delegates complex tasks to specialized modules; and an agentic memory mechanism that enables continual learning from experience.
Learn more
Appsmith
Appsmith is an open-source low-code platform designed to help businesses rapidly build custom internal tools and applications. With a drag-and-drop interface and extensive integration capabilities, Appsmith simplifies the development of dashboards, admin panels, and CRUD applications. Developers can also customize functionality using JavaScript, while seamless integration with databases and APIs makes it highly versatile. It supports self-hosting and enterprise-grade security features such as role-based access controls, audit logging, and SOC 2 compliance, making it suitable for organizations of all sizes.
Appsmith's AI-powered agent platform enables businesses to build custom conversational agents tailored to their specific needs. These agents can be embedded into various business workflows, enhancing support, sales, and customer success teams. By leveraging data-driven AI, the platform automates tasks and scales operations efficiently.
Learn more
Gemini 2.5 Computer Use
Introducing the Gemini 2.5 Computer Use model, a specialized agent model built on top of Gemini 2.5 Pro’s visual reasoning capabilities, designed to interact directly with user interfaces (UIs). It is exposed via a new computer-use tool in the Gemini API, with inputs that include the user’s request, a screenshot of the UI environment, and a history of recent actions. The model generates function calls corresponding to UI actions like clicking, typing, or selecting, and may request user confirmation for higher-risk tasks. After each action is executed, a new screenshot and URL are fed back into the model to continue the loop until the task completes or is halted. It is optimized primarily for web browser control and shows promise for mobile UI interaction, though it is not yet suited for desktop OS-level control. In benchmarks across web and mobile control tasks, Gemini 2.5 Computer Use outperforms leading alternatives, delivering high accuracy at lower latency.
Learn more
IBM watsonx Assistant
IBM watsonx Assistant (Formerly Watson Assistant) is a market-leading enterprise conversational AI platform that allows you to build intelligent virtual and voice assistants that can provide customers with fast, consistent and accurate answers across any messaging platform, application, device or channel. Using artificial intelligence and large language models, watsonx Assistant learns from customer conversations, improving its ability to resolve issues the first time while removing the frustration of long wait times, tedious searches and unhelpful chatbots.
Most chatbots try to mimic human interactions, frustrating customers when a misunderstanding arises. IBM watsonx Assistant is more than a chatbot. It knows when to search for an answer from a knowledge base, when to ask for clarity and when to direct users to a human agent for more assistance. And since it can be deployed in any cloud or on-premises environment – smarter AI is finally available wherever you need it.
Learn more