Qt / C++ infos

• Qt 6.11.1 Released

  Qt 6.11.1 is now available for download. As a patch release, Qt 6.11.1 doesn’t introduce new features, but it delivers around 450 bug fixes, security improvements, and quality enhancements on top of Qt 6.11.0. For a full overview of the most notable changes, take a look at the Qt 6.11.1 release notes.

• Qt Creator 19.0.2 released

  We are happy to announce the release of Qt Creator 19.0.2!

  The release fixes switching to English as the UI language in Qt Creator on systems with a non-English locale as well as a few other issues.

• AI Assisted Design in Qt Design Studio: AI Assistant Just Got Smarter

  

  Qt Design Studio 4.8.2 ships a major upgrade to the AI assistant, transforming it into a fully agentic AI and taking AI-assisted design to the next level. It now has access to your entire QML project and can autonomously read, write, and refactor your files to complete tasks end to end.

• From Classroom to Code II: Innovative Qt Apps by Future Developers

  

  Last year, we shared the story of a new collaboration with the Cologne University of Applied Sciences(German: TH Köln) for a new course titled Engineering Desktop Applications with C++ and Qt (EDA). The first edition gave students the chance to explore modern C++ and Qt development in a hands-on setting, with teams designing and building their own music player application.

  Now, the collaboration has successfully entered its second round.

• Introducing the Documentation MCP Tool for Qt

  

  How a Documentation MCP Tool Saves LLM Token Usage

  Every time an AI agent searches the web for Qt documentation today, it receives full HTML pages loaded with navigation chrome, cookie banners, related-article sidebars, and search-engine snippets that have nothing to do with the answer - burning thousands of LLM tokens before a single line of useful content appears. Qt's new official Model Context Protocol (MCP) tool for Qt documentation solves this directly.

• Introducing the QML Coding Skill for Agentic Workflows

  

  The Challenge: Elevating AI-Generated QML to Best-Practise Quality

  Frontier Large Language Models have become genuinely capable QML authors. Benchmarks show models like Claude, GPT, and Gemini achieving between 75% and 86% accuracy on the QML100 benchmark for single-turn coding tasks - a result that reflects the depth of Qt’s open-source ecosystem and the decades of publicly available QML code that has served as training material. For everyday UI components, a well-prompted AI agent can produce working, readable QML on the first attempt.

• Qt Creator 20 Beta released

  We are happy to announce the release of Qt Creator 20 Beta!

• Security advisory: Type confusion and heap-buffer-overflow vulnerability in Qt SVG marker handling impacts Qt

  Type Confusion and Heap-based Buffer Overflow vulnerability in the SVG marker and mask handling of the Qt SVG module has been discovered and has been assigned the CVE idCVE-2026-6210.

• Qt Design Studio 4.8.2 Released

  

  Qt Design Studio 4.8.2 Is Here!

  Following our 4.8.1 release, which introduced the Qt Design Studio AI Assistant in beta, we are back with a significant evolution of that feature, along with a few other updates. The 4.8.1 release laid the groundwork, a prompt-based tool that could generate QML from a natural language description or an image. That was a strong foundation, and the feedback we received helped shape where we took it next. In 4.8.2, the assistant has been rebuilt around a fundamentally more powerful architecture, taking AI-assisted design to the next level.

  Qt Design Studio Goes Agentic

  With 4.8.2, Qt Design Studio takes a major step forward by introducing a fully agentic AI Assistant powered by the Model Context Protocol (MCP), an open standard for connecting AI models to external tools and data sources.
  
  This shift transforms the assistant from a passive helper into an active collaborator. Instead of working on a single file, it now understands your entire project structure and can operate across it using a rich set of MCP tools: reading files, creating components, modifying existing ones, and more.
  
  When you describe a goal, the assistant enters an agentic loop. It plans the task, selects the appropriate tools, executes them, evaluates the results, and continues iterating until the objective is complete. Every step is logged in the chat, so you can follow the process. Built on MCP, the assistant is designed to be extensible and future-proof, enabling integrations with external MCP server.
  
  The assistant supports leading models from Anthropic, Google, and OpenAI, and you can switch between providers within the same conversation. The agentic AI assistant is available to all Qt Design Studio users, we encourage you to try it out and share your feedback.

  
  

  Agentic AI at Work: Medical UI demo Created from a Single Prompt

  Qt Kit Updated to 6.8.7

  This release also bumps the bundled Qt Kit from 6.8.5 to 6.8.7, picking up the latest stability and maintenance improvements from the Qt 6.8 series.

  Further Information

  • Our change log contains the full list of fixes and improvements included in this release.
  • If you run into any bugs or usability issues, please report them in the issue tracker — your feedback helps us improve every release.
  • New to Qt Design Studio? Explore the online documentation or head to the learning portal to get up to speed.

  We look forward to hearing what you build with the new agentic assistant!

• Introducing the QML Profiler Skill for Agentic Development

  

  Instead of a painstaking row-by-row or slow flame graph reviews, the QML profiler skill for agentic development allows developers to delegate code performance profiling to AI agents.
  
  The skill guides the developer through the workflow, triggers the QML profiler, crunches through the resulting raw data, presents the performance bottlenecks in a concise report, and suggests improvements.
  
  The skill targets 2D Qt Quick applications and supports four profiling modes — rendering, logic, memory, and full. It can also analyze an existing trace file directly, without re-running the application, for example, if the performance trace has been run on the target hardware.

  Video: QML profiling of shopping list app in Claude Code CLI  (Some sequences are shortened or accelerated)