I’m excited to tell you that AI Runner v4.1.2 is now available to download. It’s been 3 months since the last release and much has changed. Let’s dive right in to the changelog:

🧠 AI & Model Improvements

• 🗣️ New TTS & STT Support: Added OpenVoice, SpeechT5 voice selection, and fallback to eSpeak when others fail.
• 🧠 Mistral Support: Integrated Mistral 8B agent with enhanced memory and conversation handling.
• 🧠 Better RAG Handling: Improved performance, caching, and reloading of RAG (Retrieval-Augmented Generation).
• 🗃️ Agent Tools Upgraded: ReActAgentTool, SQLite-backed memory, dynamic UI rendering, and better agent abstraction.
• 🎨 Improved SDXL & Turbo Handling: Fixes for inpainting, model scanning, and better support for SDXL Turbo.

🖥️ GUI & UX Enhancements

• 🎛️ System Tray Support: Minimize AI Runner to the system tray with smooth show/hide transitions.
• 🪟 Improved Load & Start Time: Faster GUI loading and startup experience.
• 🎨 Canvas Overhaul: Smooth scrolling, dragging, and better grid alignment for a more fluid visual interface.
• 🖱️ Icon & UI Polish: Fixed cursor switching, better tab handling, and collapsible panels behaving properly.
• 📜 New Settings Views: Moved GUI elements to gui/ folder, cleaner styles, and dynamic sliders.

🐳 Docker & Packaging Overhaul

• 📦 Massive Docker Rework: Rebuilt the Docker system for cross-platform builds with reduced image sizes.
• 🐧 Linux Build Support: Official Linux builds now working with correct user permissions and paths.
• 🔧 New Dev Tools: Added developer-friendly scripts, setup automation, and better local install instructions.

🛠️ Refactoring & Code Quality

• 🧹 LLM, TTS, STT Refactors: Modularized handlers, improved type hints, and added full test coverage.
• 🧪 Expanded Tests: Increased test coverage across key modules including agents, filters, and widgets.
• 🧼 General Cleanup: Removed hundreds of unused imports, dead files, and unnecessary variables.
• 📚 Improved Documentation: Updated README, CONTRIBUTING guide, and added license info for new models.

🐛 Bug Fixes

• 🧠 Fixed double responses from agents and LLMs.
• 🖼️ Fixed image prompt bugs and stable diffusion crashes.
• 🔊 Resolved issues with TTS not syncing with STT.
• 🪪 Corrected handling of usernames, memory overrides, and system prompts.
• 🧱 Fixed startup crashes related to permissions, paths, and missing packages.

🌐 Infrastructure & Build

• 🚀 CI/CD Revamp: Moved all builds to GitHub Actions and added self-hosted runner support.
• 🔑 Env Management: Added better handling of .env files, removed old secrets, and cleaned up var logic.
• 🛠️ Improved Logging & Debugging: Added structured logs, error messages, and log level overrides.

🧬 Experimental & Advanced Features

• 🧪 Toggle to disable database chat store & setup wizard
• 🧬 Summarization with Summy for conversations
• 🧠 Dynamic window generation via agents
• 🧪 ControlNet and Stable Diffusion enhancements
• 🪛 Plugin support and new abstractions for LLM tasks

As always, thank you for using AI Runner — and if you haven’t tried it yet, grab the latest version here from Github or the packaged version here on Itch.