The latest point release of Ollama, version 0.32.4, expands hardware support by enabling the Laguna model series on Apple GPUs through the MLX engine. This means self-hosted users with Apple Silicon can now run these models with full hardware acceleration, tapping into the performance and efficiency of the Metal-backed MLX runtime that has already proven […]
Important: Please read the migration guide before upgrading. Traefik v3.7.9 delivers a set of targeted bug fixes and documentation improvements to enhance stability and clarify migration steps. This release addresses several issues across the IngressNGINX provider, middleware, and server components, ensuring smoother operation in self-hosted environments. Bug Fixes The IngressNGINX provider received a fix for
Traefik v3.7.9: Critical Fixes and Documentation Updates Read More »
Released on July 24, 2026, the latest patch release for n8n, version 2.32.4, brings two important fixes for users leveraging the platform’s AI capabilities. First, the AI Assistant’s verification step now properly falls back to the model specified in the workflow run when the default configuration is unavailable. Previously, if the designated model wasn’t accessible,
n8n 2.32.4 Patch Addresses AI Assistant Looping and Model Fallback Read More »
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 »
The latest Ollama update fixes a frustrating bug where model downloads would stall before sending any data. It also resolves an issue with GLM tool calls being silently dropped at the end of generation, ensuring that tool interactions are reliable. Integration improvements include the restoration of Claude Code Channels and a fix for Anthropic thinking
Ollama v0.32.3: Smooth Downloads, Expanded GPU Support, and Laguna 2.1 Integration Read More »
This round of Home Assistant Core updates brings targeted fixes that will make life easier for self-hosted users relying on specific integrations. The ProxmoxVE component now correctly handles authentication when a realm name contains uppercase letters, resolving a login hiccup that could block access to your virtual environment dashboard. Similarly, the Enphase Envoy integration has
Latest Home Assistant Core Improvements: Smoother Integrations and Upgraded Dependencies Read More »
The latest patch for n8n, version 2.32.3, addresses a single but important issue in the editor. Users were unable to set up credentials for agent channels, a feature that enables seamless integration with external agents. This fix restores that functionality, ensuring that self-hosted deployments can continue to smoothly configure and use agent channels. No other
n8n 2.32.3 Patch Restores Agent Channel Credential Setup Read More »
This ESPHome release introduces a useful new option for Sen5x sensor users, who can now manually specify the sensor model if automatic detection fails. Alongside this, a bug affecting partial screen updates on MIPI SPI displays has been resolved, and the bundle compilation process now correctly remaps absolute file paths, preventing build errors when working
ESPHome Update Improves Sensor Configuration and Squashes Bugs Read More »
The langchain-openrouter package has been updated to version 0.2.7, bringing a wave of routine but essential syncs that keep your self-hosted setup aligned with the latest OpenRouter offerings. Central to this release are multiple refreshes of model profile data — the internal catalog that describes which models are available, their capabilities, and how to interact
LangChain-OpenRouter 0.2.7 Keeps Model Profiles and Dependencies Current Read More »
The latest update to the Metal backend extends Leaky ReLU activation with support for half-precision (f16) floating-point data. This enables efficient computation and reduced memory usage when running models on Apple GPUs, particularly benefiting inference tasks where lower precision is acceptable. Users leveraging Metal acceleration can now take advantage of faster matrix operations without sacrificing
Metal Backend Adds Half-Precision Support for Leaky ReLU Read More »
