
From June through July, LobeHub focused on two things: making tools easier to discover and making search more flexible. The new MCP Marketplace brings one-click plugin installation to desktop, while expanded search providers and authentication options give teams more choice in how they work.
MCP Marketplace: discover and install tools faster
Finding and installing MCP plugins used to require manual setup. Now the MCP Marketplace brings one-click installation directly to the desktop app. Browse available tools, see what they do, and add them to your workspace without leaving the interface.
This makes the plugin ecosystem more accessible鈥攅specially for teams who want to extend their Agents without diving into configuration files or command-line steps.
More ways to search and authenticate
Search coverage now includes Brave, Google PSE, and Kagi as built-in options, plus Vertex AI Google Search Grounding for grounded generation workflows. You can choose the provider that fits your accuracy, speed, and privacy needs.
On the authentication side, Amazon Cognito and Google SSO are now available as identity providers. Teams already using these systems can connect LobeHub without adding another set of credentials. Page access protection is also included, so you can control who sees what based on their sign-in status.
Runtime improvements
This cycle also brings v0 (Vercel) provider support and an analytics event-tracking framework for better visibility into usage patterns.
Improvements and fixes
- Refined mobile model selector layout and text overflow handling
- Improved loading animation transitions
- Optimized Gemini thinkingBudget configuration and reasoning_effort parameter handling
- Added Browserless blockAds and stealth parameters for cleaner search results
- Fixed Mermaid rendering issues in Firefox
- Improved multi-monitor window opening behavior on desktop
- Fixed theme-related edge cases and optimized chunked loading
- Added transition animation toggle for response rendering
Version details
Features
What's improved
- v1.97.10Update i18n.
- v1.97.9Integrate Amazon Cognito for user authentication.
- v1.97.7Add google search grounding for Vertex AI.
- v1.97.6Replace utility-types with type-fest.
- v1.97.5Fix: solve the loading was strange spin when switch show.
- v1.97.4Add grok-4-0709 model from xAI, fix theme issue in desktop.
- v1.97.2Implement data analytics event tracking framework.
- v1.96.20Add MCP_TOOL_TIMEOUT env and improve debug usage guide.
- v1.96.18Files hello pages should scroll.
- v1.96.16Update i18n.
- v1.96.14Migrate to @google/genai SDK for Google Gemini API and Vertex AI.
- v1.96.13Update i18n.
- v1.96.12Add DeepResearch models from OpenAI.
- v1.96.8Optimized Gemini thinkingBudget configuration.
- v1.96.7Add blockAds & stealth params for Browserless.
- v1.96.6Update i18n.
- v1.96.2Update i18n.
- v1.94.17Update i18n.
- v1.94.15Update model card for Gemini 2.5 Pro via OpenRouter.
- v1.94.14Update i18n.
- v1.94.13Update Gemini 2.5 Pro, Flash GA models. Add Gemini 2.5 Flash-Lite Preview model.
- v1.94.12Add MiniMax-M1 model.
- v1.94.9Add kimi-thinking-preview model from Moonshot.
- v1.94.7Add Doubao Seed 1.6 model.
- v1.94.5Support web_search_preview & fix some bug form OpenAI Response API.
- v1.94.4Transition animation switch.
- v1.94.1Update pplx abilities tags, support vision.
- v1.93.3Refactor branding info.
What's fixed
- v1.97.1Fix locale hydration error in SSR.
- v1.96.19Pin officeparser@5.1.1 to fix server error.
- v1.96.18Change the wrong github checkmodel name.
- v1.96.15Wrong Gemini 2.5 Pro thinkbudget.
- v1.96.12Pin antd@5.26.2 to fix build error.
- v1.96.10Fix desktop chunk issue.
- v1.96.9Google Gemini tools declarations.
- v1.96.5Remove unsupported parameters of Hunyuan.
- v1.96.1Fix MiniMax-M1 reasoning tag missing.
- v1.96.0Fix inputTemplate behavior.
- v1.94.16Correctly pass reasoning.summary.
- v1.94.11Enhance the multi-display window opening experience.
- v1.94.10Improve chat selectors and enhance topic handling logic.
- v1.94.8Correctly handle reasoning_effort.
- v1.94.6Abort the Gemini request correctly & Add openai o3-pro.
- v1.94.2Update Gemini range of thinkingBudget.
- v1.94.0Restore reasoningEffort in setting.
