In a strategic move to advance open-source development in medical AI, Google DeepMind and Google Research have introduced two new models under the MedGemma umbrella: MedGemma 27B Multimodal, a large-scale vision-language foundation model, and MedSigLIP, a lightweight medical image-text encoder. These additions represent the most capable open-weight models released to date within the Health AI…
Perplexity, a company already recognized for redefining how users interact with information through AI-powered search, has announced the launch of Comet, an ambitious AI-native web browser. Designed with an AI-first architecture, Comet is set to revolutionize how users navigate, retrieve, and interact with web content by combining browsing with real-time contextual assistance, summarization, and intelligent…
Salesforce AI Research has introduced GTA1, a new graphical user interface (GUI) agent that redefines the state-of-the-art in agentic human-computer interaction. Designed to autonomously operate in real operating system environments such as Linux, GTA1 addresses two critical bottlenecks in GUI agent development: ambiguous task planning and inaccurate grounding of actions. With a 45.2% task success…
Microsoft has officially open-sourced the GitHub Copilot Chat extension for Visual Studio Code (VS Code), placing a previously premium AI-powered coding assistant into the hands of developers—free of charge. Released under the permissive MIT license, the entire feature set that once required a subscription is now accessible to everyone. This shift represents a major milestone…
Hugging Face just released SmolLM3, the latest version of its “Smol” language models, designed to deliver strong multilingual reasoning over long contexts using a compact 3B-parameter architecture. While most high-context capable models typically push beyond 7B parameters, SmolLM3 manages to offer state-of-the-art (SoTA) performance with significantly fewer parameters—making it more cost-efficient and deployable on constrained…
BeeAI FrameworkIn this tutorial, we explore the power and flexibility of the beeai-framework by building a fully functional multi-agent system from the ground up. We walk through the essential components, custom agents, tools, memory management, and event monitoring, to show how BeeAI simplifies the development of intelligent, cooperative agents. Along the way, we demonstrate how…
Google has released the MCP Toolbox for Databases, a new open-source module under its GenAI Toolbox aimed at simplifying the integration of SQL databases into AI agents. The release is part of Google’s broader strategy to advance the Model Context Protocol (MCP), a standardized approach that allows language models to interact with external systems—including tools,…
In this advanced tutorial, we aim to build a multi-agent task automation system using the PrimisAI Nexus framework, which is fully integrated with the OpenAI API. Our primary objective is to demonstrate how hierarchical supervision, intelligent tool utilization, and structured outputs can facilitate the coordination of multiple AI agents to perform complex tasks, ranging from…
Osmosis AI has open-sourced Osmosis-Apply-1.7B, a fine-tuned variant of Qwen3-1.7B, designed to perform highly accurate and structured code merge tasks. Drawing inspiration from IDE agents like Cursor’s “instant apply,” Osmosis-Apply-1.7B is optimized for context-sensitive, function-level code edits. The model achieves strong performance with fewer parameters compared to much larger foundation models by leveraging code-specific formatting…
ByteDance, the Chinese tech giant behind TikTok and other global platforms, has officially released Trae Agent, a general-purpose software engineering agent powered by large language models (LLMs). Designed to execute complex programming tasks via natural language prompts, Trae Agent offers a highly capable and extensible Command-Line Interface (CLI), redefining how developers can interact with their…