Open Computer Agent

Gobii is a cloud-hosted platform that enables you to spin up fully managed browser-automation agents via API, allowing tasks like web-based research, form-filling, data extraction, and multi-step workflows to be automated at scale. These agents operate like “always-on employees” that can browse websites, even those without APIs, navigate dynamic content, handle JavaScript, and even rotate proxies automatically. Users can create agents, assign them prompts or tasks, and retrieve structured JSON outputs or live previews of the agent’s browser actions. Gobii supports synchronous and asynchronous task execution, secret handling for things like login credentials, schema-enforced output validation, and integrates with popular programming languages (Python, Node.js) for seamless implementation. The platform emphasises scalability (hundreds of tasks in parallel), enterprise-grade security (audit logs, proxies, task management), and a simple developer experience.

Qwen2.5-VL is the latest vision-language model from the Qwen series, representing a significant advancement over its predecessor, Qwen2-VL. This model excels in visual understanding, capable of recognizing a wide array of objects, including text, charts, icons, graphics, and layouts within images. It functions as a visual agent, capable of reasoning and dynamically directing tools, enabling applications such as computer and phone usage. Qwen2.5-VL can comprehend videos exceeding one hour in length and can pinpoint relevant segments within them. Additionally, it accurately localizes objects in images by generating bounding boxes or points and provides stable JSON outputs for coordinates and attributes. The model also supports structured outputs for data like scanned invoices, forms, and tables, benefiting sectors such as finance and commerce. Available in base and instruct versions across 3B, 7B, and 72B sizes, Qwen2.5-VL is accessible through platforms like Hugging Face and ModelScope.