🚀 4 Months of Evolution is Here.
In the past 4 months, we’ve shipped dozens of updates. From low-level protocol adaptations to top-level UI overhauls, every line of code has been rewritten with one goal: to build a smarter, faster, and more secure AI assistant for you.
🧠 Deep Intelligence & Reasoning
Visible Thinking: We now support streaming reasoning processes for most major model providers. Watch your AI’s thought logic unfold in real-time.
Multimodal Power: Upload documents and capture screenshots directly. Give your LLM more context to work with 📄&📸
Expanded Protocols: Added native support for OpenAI Responses API and Google API for enhanced compatibility.
✨ Personalization: From Tool to Assistant
🎨UI Overhaul: A modern, sleek main window layout designed for focus and aesthetics.
Custom AI Personas: Create multiple assistants with unique icons, names, and system prompts. Switch between them instantly via hotkeys or mouse wheel.
Polished UX: Drag-and-drop sorting, adjustable font sizes, message editing/resending, and remembered window positions.
🌐Auto-i18n: Powered by GPT 4.1-mini, we’ve added support for German, Spanish, French, Italian, Japanese, Korean, Russian, Turkish, and Traditional Chinese.
🔌 Ecosystem Connectivity: The Ultimate Hub
MCP Ecosystem: Full support for importing Model Context Protocol (MCP) tools. Now running sub-agents and task management plugins for complex workflows.
Professional Search: Integrated Tavily, Jina, SearXNG, and UniFuncs for high-quality, real-time web data.
⚡️Local Power (Windows): Deep integration with Everything. Find files and read content across your local machine at lightning speed.
🛡️ Performance & Security
Leaner & Faster: Optimized Markdown and LaTeX rendering with lower memory usage. The app size has been reduced by 50%!
Security First: Introduced digital signatures and a user-confirmation mechanism for high-privilege plugins to keep your data safe.
❤️ Community-Driven
A massive thank you to our GitHub contributors, especially TheNotoBarth and jimfengnpu (Linux cross-platform dev), and everyone else who contributed. Special thanks to the users who sponsored our Apple Developer Program fee—your support keeps us going!
📅 What’s Next?
🍎 macOS Version: Currently in the second round of testing. We are squashing the final bugs to ensure a smooth launch very soon.
AI Memory: Long-term memory is on the roadmap to make your assistant truly personal.
Scenario-Specific Features: More official services optimized for your specific workflows are coming.
Stay tuned! 🚀
Replies