release notes

imagem 29

Home Assistant Core Update: Integration Fixes and Library Bumps

This Home Assistant Core update delivers a broad set of fixes aimed at improving reliability across many smart home integrations. Among the notable corrections, Teslemetry now converts streamed tire pressure and isolation resistance values to their declared units, and Husqvarna Automower handles inconsistent API responses more gracefully. TP-Link Omada resolves an issue with switch port

Home Assistant Core Update: Integration Fixes and Library Bumps Read More »

imagem 18

n8n 2.34.3: More Robust Agent Handling and Refined User Interface

n8n version 2.34.3 arrives with a handful of focused bug fixes that improve stability and usability for self-hosted users. This patch release addresses issues in agent workflows, editor dropdowns, and backend communication, making everyday automation tasks a bit smoother. Smarter Agent Workflows Agents can now handle unexpected data more gracefully. The update ensures that any

n8n 2.34.3: More Robust Agent Handling and Refined User Interface Read More »

imagem 11

n8n 2.34.1: Stability Improvements for Self-Hosted Workflows

n8n 2.34.1 – August 5, 2026 The latest patch for n8n brings two key fixes that self-hosted users will appreciate, focusing on reliability and a smoother interface. First, a core improvement now automatically recovers unresponsive task runners—the background processes that handle heavy-lifting in your workflows. If a task runner hangs or stops responding, n8n can

n8n 2.34.1: Stability Improvements for Self-Hosted Workflows Read More »

imagem 44

n8n 2.33.0 Brings Enhanced AI Builder, Workflow Review System, and More

n8n version 2.33.0, released on July 28, 2026, delivers a massive set of updates focusing on the AI Builder, core stability, editor refinements, and new node functionalities. This release includes over 100 fixes and features designed to improve the self-hosted automation experience. AI Builder Gets Smarter and More Robust The AI Builder receives significant attention

n8n 2.33.0 Brings Enhanced AI Builder, Workflow Review System, and More Read More »

imagem 41

llama.cpp Release b10159 Brings FWHT Kernel to Metal Backend

We’re excited to announce a new build of llama.cpp (b10159), which includes a performance-boosting addition for Apple Silicon users. This release introduces the Fast Walsh-Hadamard Transform (FWHT) kernel into the Metal backend, improving the efficiency of certain mathematical operations during model inference. While the change is low-level, it helps streamline computation on macOS and iOS

llama.cpp Release b10159 Brings FWHT Kernel to Metal Backend Read More »

imagem 31

LangChain-OpenAI v1.4.1: LangSmith Gateway Support and Model Profile Fix

LangChain-OpenAI version 1.4.1 is a minor release that builds on the previous 1.4.0 with a couple of practical improvements. It focuses on better integration with LangSmith’s infrastructure and correcting a model configuration quirk. A notable new feature is the ability to route API calls through LangSmith’s gateway by simply setting an environment variable. This makes

LangChain-OpenAI v1.4.1: LangSmith Gateway Support and Model Profile Fix Read More »

imagem 9

langchain-xai 1.3.0: Reasoning Control, Custom Endpoints, and Security Fixes

The langchain-xai library version 1.3.0 introduces several notable features for self-hosted users. A new reasoning_effort parameter has been added as a standard chat model option, allowing you to adjust the depth of reasoning for xAI models. Additionally, you can now set a custom API base URL via the base_url alias or the XAI_API_BASE environment variable,

langchain-xai 1.3.0: Reasoning Control, Custom Endpoints, and Security Fixes Read More »