AI Agents

Google launched a Model Context Protocol (MCP) server for Data Commons, exposing the undertaking’s interconnected public datasets—census, well being, local weather, economics—via a standards-based interface that agentic methods can question in pure language. The Data Commons MCP Server is out there now with quickstarts for Gemini CLI and Google’s Agent Development Kit (ADK). What was…

Google has launched a public preview of “Chrome DevTools MCP,” a Model Context Protocol (MCP) server that lets AI coding brokers management and examine a actual Chrome occasion—recording efficiency traces, inspecting the DOM and CSS, executing JavaScript, studying console output, and automating consumer flows. The launch straight targets a well-known limitation in code-generating brokers: they…

Parlant is a framework designed to assist builders construct production-ready AI brokers that behave persistently and reliably. A typical problem when deploying giant language mannequin (LLM) brokers is that they usually carry out nicely in testing however fail when interacting with actual customers. They might ignore rigorously designed system prompts, generate inaccurate or irrelevant responses…

The Universal Tool Calling Protocol (UTCP) is a light-weight, safe, and scalable method for AI brokers and functions to seek out and name instruments immediately, with out the want for extra wrapper servers. Key Features Lightweight and safe – Allows instruments to be accessed immediately, avoiding pointless center layers. Scalable – Can help numerous instruments…

Coral Protocol has launched Coral v1 of its agent stack, aiming to standardize how builders uncover, compose, and function AI brokers throughout heterogeneous frameworks. The launch facilities on an MCP-based runtime (Coral Server) that permits threaded, mention-addressed agent-to-agent messaging, a developer workflow (CLI + Studio) for orchestration and observability, and a public registry for agent…

xAI launched Grok-4-Fast, a cost-optimized successor to Grok-4 that merges “reasoning” and “non-reasoning” behaviors right into a single set of weights controllable by way of system prompts. The mannequin targets high-throughput search, coding, and Q&A with a 2M-token context window and native tool-use RL that decides when to browse the net, execute code, or name…

Sensible Agent is an AI analysis framework and prototype from Google that chooses each the motion an augmented actuality (AR) agent ought to take and the interplay modality to ship/verify it, conditioned on real-time multimodal context (e.g., whether or not arms are busy, ambient noise, social setting). Rather than treating “what to recommend” and “tips…