LobeHub
LobeHub

Changelog

Track new features, fixes, and improvements in LobeHub.

November Update - Four New Model Providers

November Update - Four New Model Providers

This month's provider expansion adds four new options for running models. Teams can now choose from a wider range of hosting environments and compare outputs across different ecosystems without switching platforms.

New providers available

The following providers are now supported:

  • Gitee AI - Model hosting with Chinese developer ecosystem integration
  • InternLM - Open-source large language models from Shanghai AI Laboratory
  • xAI - Grok and other models from xAI
  • Cloudflare Workers AI - Edge-deployed models running on Cloudflare's global network

What this enables

Use these additions to:

  • Route requests to providers based on latency, cost, or compliance requirements
  • Compare model behavior across different hosting environments
  • Deploy closer to users with edge-hosted options

Feedback

Need additional providers? Tell us which ones to prioritize in GitHub Discussions.

v1.33.0 ~ v1.30.1

Export Conversations as Markdown or OpenAI JSON

Export Conversations as Markdown or OpenAI JSON

Version 1.28.0 makes conversation exports more useful. You can now download chats as Markdown for documentation or OpenAI-format JSON for debugging and training. No more copy-pasting or reformatting by hand.

Better documentation workflows

The Markdown export turns conversations into clean, readable documents. Writers can capture useful exchanges and move them directly into notes, wikis, or reports without manual cleanup.

Exporting Conversations as Markdown Text
Exporting Conversations as Markdown Text

API-ready JSON for developers

The JSON export follows the OpenAI messages format. This means you can drop exported conversations directly into API debugging tools or use them as structured training data for fine-tuning.

Tool calling data is preserved in its original structure, which helps when analyzing or improving how agents use external tools.

Exporting Conversations as JSON in OpenAI API Specification
Exporting Conversations as JSON in OpenAI API Specification

Improvements and fixes

  • Added Markdown export option for conversation sharing
  • Added OpenAI-format JSON export with full message structure
  • Tool calling data preserved in original format during export
v1.28.0 ~ v1.26.1

Persistent Agent Sidebar: Faster Access, Less Context Switching

LobeHub Adds a Persistent Agent Sidebar

In v1.26.0, LobeHub adds a persistent Agent sidebar to make high-frequency Agents easier to reach during active conversations. Instead of jumping between lists, you can keep your key Agents visible and switch with less friction.

Tighter conversation workflow

This update focuses on reducing small interaction costs in everyday chat:

  • Quick switching — Use keyboard shortcuts to move between Agents faster
  • More chat space — When the sidebar is active, the conversation list hides to free up room for messages
  • Synced pinned Agents — Your pinned Agents automatically appear in the sidebar so priority items stay in view
Sidebar Display Effect
Sidebar Display Effect
Conversation Interface Effect
Conversation Interface Effect

How to enable

This capability is currently experimental and disabled by default. To try it in self-hosted setups, enable it with:

FEATURE_FLAGS=+pin_list

The Cloud version already has this enabled. If you try it, share feedback in GitHub Discussions so we can keep improving the experience.

Why we built it

The goal of this release is straightforward: improve focus and reduce small interaction costs in everyday chat. By keeping frequently used Agents close at hand and reclaiming screen space for messages, the interface supports longer, more concentrated conversations.

v1.26.0 ~ v1.19.1

LobeHub v1.19: Artifacts, Discovery, and More Models

LobeHub Enters the Era of Artifacts

LobeHub v1.19 is now live. This release brings a major step forward for day-to-day assistant usage, with stronger creation workflows, broader model access, and a redesigned way to discover what you can do next.

Create with Artifacts

LobeHub now replicates the core Claude Artifacts experience. You can generate and interact with rich content directly in the conversation:

  • SVG graphics — Generate and display vector graphics that render in real time
  • HTML pages — Create and preview interactive web pages without leaving the chat
  • Rich documents — Produce formatted documents in multiple output formats

Python code execution is also in development and planned for a future release. Once available, you will be able to combine Claude Artifacts with OpenAI Code Interpreter, further extending what you can build with your assistant.

Artifacts Feature Showcase
Artifacts Feature Showcase

Redesigned discovery page

The discovery page has been rebuilt with richer content categories to help you explore AI capabilities more naturally:

  • AI Assistant Marketplace
  • Plugin Showcase
  • Model List
  • Provider Introductions

The new layout raises information density while making capabilities easier to browse. We plan to expand this page further with knowledge base sharing, Artifacts showcases, and curated conversation sharing.

GitHub Models provider support

Thanks to community contributor @CloudPassenger, LobeHub now supports GitHub Models as a provider. To start using it:

  1. Prepare a GitHub Personal Access Token (PAT)
  2. Configure provider information in settings
  3. Start using free models available on GitHub Models

This significantly expands the available model pool and gives you more choices for different conversation scenarios.

Improvements and fixes

  • Added full Artifacts support for SVG, HTML, and document generation
  • Redesigned discovery page with marketplace, plugins, models, and providers
  • Added GitHub Models provider support
  • Preparing Python code execution feature for upcoming release
  • Planned expansion of discovery page with knowledge base and Artifacts sharing

Credits

Huge thanks to community contributor @CloudPassenger for the GitHub Models integration.

v1.19.0 ~ v1.17.1

OpenAI O1 Series Models Now Available

LobeHub Adds Support for OpenAI O1 Series Models

LobeHub v1.17.0 now supports OpenAI's newly launched O1 series models. This update is available for both community edition users and Cloud version subscribers.

The O1 series brings stronger performance in the areas users rely on most: code writing and comprehension, mathematical problem solving, and more precise task execution. You can start using these models immediately without waiting or extra configuration.

New model support

This release adds two models from the O1 family:

  • OpenAI o1-preview — Full reasoning capabilities for complex tasks
  • OpenAI o1-mini — Faster, cost-effective option for everyday work

Stronger where you need it

The O1 series excels at structured reasoning tasks. Use these models when you need:

  • Code that compiles and runs correctly the first time
  • Step-by-step mathematical derivations with explanations
  • Precise execution of multi-step instructions

Both models are available now in the model selector for all LobeHub users.

How to start using

  • Cloud version subscribers can use O1 models immediately
  • Self-hosted users should update to v1.17.0 to access the new models

With this release, LobeHub continues to track the latest model ecosystem. We look forward to seeing what you build with the O1 series.

v1.17.0 ~ v1.12.1
LobeHub

Super-Agents on Your Team

Bring Super-Agents onto your team, starting today.