← all releases
Google·Feb 10, 2026·Early Preview·open source
WebMCP
WebMCP is an initiative by Google to standardize how AI agents interact with websites, aiming to enhance the efficiency and reliability of these interactions. By defining structured tools, WebMCP enables AI agents to perform actions on websites with increased speed and precision.
MLMCP
overview
WebMCP is an initiative by Google to standardize how AI agents interact with websites, aiming to enhance the efficiency and reliability of these interactions. By defining structured tools, WebMCP enables AI agents to perform actions on websites with increased speed and precision.
key features
- 01Declarative API for standard actions
- 02Imperative API for complex interactions
- 03Enhanced AI agent workflows
- 04Improved website-agent communication
- 05Supports diverse use cases like e-commerce and travel
related productsbrowse all →
SkyRL txopen sourceSkyRL tx is an open-source library that implements a backend for the Tinker API, enabling users to set up their own Tinker-like services on personal hardware. It supports end-to-end reinforcement learning (RL) and offers significantly faster sampling. The library is designed to be modular, allowing easy prototyping of new training algorithms, environments, and execution plans without compromising usability or speed.Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.SINQopen sourceSINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.