mirror of
https://github.com/lobehub/lobehub.git
synced 2026-09-20 04:56:13 +08:00
YuTengjing
191f3fe776
* 📝 docs: fix outdated content across the docs site Audited docs/ against the current codebase and fixed stale content that drifted after major refactors (Clerk/NextAuth → Better Auth, src/server → apps/server, src/{config,envs,locales} → packages/*, model-bank updates). - self-hosting/auth: mark removed NextAuth/Clerk pages with deprecation warnings; fix microsoft/zitadel alias claims and the Logto callback path - environment-variables & advanced: correct wrong defaults (S3_SET_ACL, AI_IMAGE_DEFAULT_IMAGE_NUM, index/proxy URLs), drop non-existent env vars and fictional feature flags, fix OIDC config guidance - development: update refactored paths, Better Auth, .mjs configs, remove the MSW section (msw is not a dependency) - providers & model examples: replace retired model ids with in-bank ones; fix comfyui frontmatter corruption - usage: rename Moderator→Orchestrator, GTD→Task, correct shortcut keys, channel capability tables, Feishu/Lark WebSocket mode - platform/migration: fix dead links, docker service name, npx/npm → bun EN and zh-CN pairs updated together. * 📝 docs: fix Logto callback path and AUTH_SECRET deprecation guidance - Revert Logto/Sealos callback URLs to /api/auth/callback/logto to match the runtime SSO redirectURI override - Narrow legacy auth Callout: AUTH_SECRET remains required for Better Auth; mark NEXT_AUTH_SECRET as deprecated in zh-CN * 📝 docs: refresh agent skills for locales, env, auth, and agentRun paths Align OSS agent guidance with post-refactor layout: - packages/locales/src/default + bun run i18n - packages/env/src for env schemas (@/envs alias) - spa-auth shell + src/routes/auth segments - chat agentRun/transports/hetero instead of aiChat * 📝 docs: document APP_URL as required for Better Auth base URL Self-hosted auth uses appEnv.APP_URL as baseURL, not request-header auto-detection. NEXT_PUBLIC_AUTH_URL remains deprecated. * 📝 docs: note self-host search provider setup for web search Built-in lobe-web-browsing needs no client plugin, but self-hosted servers still require SEARCH_PROVIDERS / SEARXNG_URL (default SearXNG). * 📝 docs: point feature guide welcome UI at AgentHome Opening message/questions on the agent chat page live in src/features/AgentHome, not Onboarding WelcomeMessage.
211 lines
10 KiB
Plaintext
211 lines
10 KiB
Plaintext
---
|
||
title: Introduction
|
||
description: >-
|
||
LobeHub is the next-generation agent harness designed to democratize AI power.
|
||
Move beyond one-off, task-driven tools and build long-term agent teammates
|
||
that grow with you in the world’s largest human–agent co-evolving network.
|
||
tags:
|
||
- LobeHub
|
||
- Getting Started
|
||
- Agent Workspace
|
||
- AI Collaboration
|
||
- Agent Teams
|
||
- Memory
|
||
- MCP
|
||
---
|
||
|
||
# Introduction
|
||
|
||
LobeHub is the next-generation agent harness designed to democratize AI power. Move beyond one-off, task-driven tools and build long-term agent teammates that grow with you in the world’s largest human–agent co-evolving network.
|
||
|
||
<Image alt={'LobeHub'} cover src={'https://hub-apac-1.lobeobjects.space/blog/assets/341c0d38baf2ddbb2ca6a1407129a62a.webp'} />
|
||
|
||
## Welcome to LobeHub
|
||
|
||
Today’s agents are one-off, task-driven tools. They lack context, live in isolation, and require manual hand-offs between different windows and models. While some maintain memory, it is often global, shallow, and impersonal. In this mode, users are forced to toggle between fragmented conversations, making it difficult to form structured productivity.
|
||
|
||
**LobeHub changes everything.**
|
||
|
||
LobeHub is a work-and-lifestyle space to find, build, and collaborate with agent teammates that grow with you. In LobeHub, we treat **Agents as the unit of work**, providing an infrastructure where humans and agents co-evolve.
|
||
|
||
---
|
||
|
||
<Image alt={'create with LobeHub'} cover src={'https://hub-apac-1.lobeobjects.space/blog/assets/2204cde2228fb3f583f3f2c090bc49fb.webp'} />
|
||
|
||
### Create: Agents as the Unit of Work
|
||
|
||
Building a personalized AI team starts with the **Agent Builder**. You can describe what you need once, and the agent setup starts right away, applying auto-configurations so you can use it instantly.
|
||
|
||
- **Unified Intelligence**: Seamlessly access any model and any modality—all under your control.
|
||
- **10,000+ Skills**: Connect your agents to the skills you use every day with a library of over 10,000 tools and MCP-compatible plugins.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/getting-started/agent'} title={'Create a Custom Agent'} />
|
||
|
||
<Card href={'/docs/usage/community/agent-market'} title={'Agent Marketplace'} />
|
||
</Cards>
|
||
|
||
---
|
||
|
||
<Image alt={'collaborate with LobeHub'} cover src={'https://hub-apac-1.lobeobjects.space/blog/assets/771ff3d30b9ef93e65e55021cc43d356.webp'} />
|
||
|
||
### Collaborate: Scale New Forms of Collaboration Networks
|
||
|
||
LobeHub introduces **Agent Groups**, allowing you to work with agents like real teammates. The system assembles the right agents for the task, enabling parallel collaboration and iterative improvement.
|
||
|
||
- **Pages**: Write and refine content with multiple agents in one place with a shared context.
|
||
- **Schedule**: Schedule runs and let agents do the work at the right time, even while you are away.
|
||
- **Project**: Organize work by project to keep everything structured and easy to track.
|
||
- **Workspace**: A shared space for teams to collaborate with agents, ensuring clear ownership and visibility across the organization.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/agent/agent-team'} title={'Agent Groups'} />
|
||
|
||
<Card href={'/docs/usage/agent/pages'} title={'Pages'} />
|
||
</Cards>
|
||
|
||
---
|
||
|
||
<Image alt={'evolve with LobeHub'} cover src={'https://hub-apac-1.lobeobjects.space/blog/assets/fe98eae9fcb6acc47c8e1fb69bdb4b50.webp'} />
|
||
|
||
### Evolve: Co-evolution of Humans and Agents
|
||
|
||
The best AI is one that understands you deeply. LobeHub features **Personal Memory** that builds a clear understanding of your needs.
|
||
|
||
- **Continual Learning**: Your agents learn from how you work, adapting their behavior to act at the right moment.
|
||
- **White-Box Memory**: We believe in transparency. Your agents use structured, editable memory, giving you full control over what they remember.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/getting-started/memory'} title={'Memory'} />
|
||
|
||
<Card href={'/docs/usage/agent/chain-of-thought'} title={'Chain of Thought'} />
|
||
</Cards>
|
||
|
||
---
|
||
|
||
## Next Steps
|
||
|
||
<Steps>
|
||
### Get started
|
||
|
||
Follow the [Quickstart](/docs/usage/getting-started/lobe-ai) to start your first conversation with Lobe AI. No setup needed.
|
||
|
||
### Build your first Agent
|
||
|
||
[Create a custom Agent](/docs/usage/getting-started/agent) tailored to your workflow. Describe what you need, and LobeHub handles the rest.
|
||
|
||
### Spin up a Group
|
||
|
||
[Assemble an Agent team](/docs/usage/agent/agent-team) to tackle complex tasks together, in sequence, parallel, or debate.
|
||
|
||
### Explore the Community
|
||
|
||
[Discover Agents](/docs/usage/community/agent-market) built by others and use them instantly.
|
||
</Steps>
|
||
|
||
---
|
||
|
||
## Make it yours
|
||
|
||
### Choose the right model for every task
|
||
|
||
Not every question needs the most powerful model.
|
||
|
||
A quick translation? A lightweight model handles it in milliseconds for a fraction of the cost. A nuanced legal analysis? Route it to the model with the deepest reasoning capabilities.
|
||
|
||
LobeHub gives you access to **70+ providers**, including GPT-5, Claude, Gemini, DeepSeek, Llama, and Qwen, from over a dozen providers. Switch models mid-conversation, or let your Agent pick the best one for each turn. If your data needs to stay on-device, you can run local models too.
|
||
|
||
Each Agent can have its own default model. Your code reviewer uses one model while your copywriter uses another, all running automatically without you making a choice each time.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/providers'} title={'AI Providers'} />
|
||
|
||
<Card href={'/docs/usage/getting-started/lobe-ai'} title={'Try Lobe AI'} />
|
||
</Cards>
|
||
|
||
### 10,000+ Skills: Connect Agents to the tools you use
|
||
|
||
An Agent that can only chat is only half the story.
|
||
|
||
With [Skills](/docs/usage/agent/skills), your Agent reads your GitHub issues, queries your database, sends a Slack message, generates a PDF, or books a meeting. All within the same conversation.
|
||
|
||
LobeHub supports the [Model Context Protocol (MCP)](/docs/usage/community/mcp-market), an open standard that connects Agents to an ever-growing ecosystem of **10,000+ tools**. Install a Skill from the marketplace in one click, or build your own and share it with the Community.
|
||
|
||
A few real-world examples:
|
||
|
||
- *"Summarize the top 5 GitHub issues and post a digest to Slack"* → your Agent reads the issues, writes the summary, sends the message.
|
||
- *"Pull this week's sales data and build a chart"* → your Agent queries the database, processes the numbers, renders a visual Artifact.
|
||
- *"Find flights to Tokyo next month under $800"* → your Agent searches, compares, and presents options with booking links.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/agent/skills'} title={'Agent Skills'} />
|
||
|
||
<Card href={'/docs/usage/community/mcp-market'} title={'MCP Marketplace'} />
|
||
</Cards>
|
||
|
||
### Resource Library: Give your Agents real knowledge
|
||
|
||
Generic AI answers are fine for generic questions. But when you need an Agent that knows *your* codebase, *your* product docs, *your* company policies, the [Resource Library](/docs/usage/agent/resources) is where you start.
|
||
|
||
Upload documents, images, spreadsheets, audio, or video. Your Agent references them during conversations, so its answers are grounded in your actual data, not just training-set knowledge. Build a knowledge base for each Agent, or share resources across your Workspace.
|
||
|
||
Imagine a customer support Agent that knows your entire help center. A legal assistant trained on your contract templates. A product manager who has read every PRD you've ever written. That's Resource Library at work.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/agent/resources'} title={'Resource Library'} />
|
||
</Cards>
|
||
|
||
### Create visuals without leaving the conversation
|
||
|
||
Need a hero image for a blog post? A diagram for your architecture doc? A quick mockup to pitch an idea?
|
||
|
||
Ask your Agent. It generates images using GPT Image, Flux, and other models, and renders them as Artifacts right in the chat. No switching to a separate design tool, no export-download-reupload cycle. The image is there, in context, next to the conversation that produced it.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/agent/artifacts'} title={'Artifacts'} />
|
||
</Cards>
|
||
|
||
### Community: Shared intelligence
|
||
|
||
LobeHub's philosophy starts with people. The [Community](/docs/usage/community/agent-market) is where thousands of creators publish Agents, Skills, and workflows for everyone to discover, install, and remix.
|
||
|
||
Found an Agent that's 80% of what you need? Install it, tweak the prompt, swap the model, add your own knowledge base, and it becomes yours. Or build something from scratch and share it back. The best ideas compound when they're open.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/community/agent-market'} title={'Agent Marketplace'} />
|
||
|
||
<Card href={'/docs/usage/community/mcp-market'} title={'MCP Marketplace'} />
|
||
|
||
<Card href={'/docs/usage/community/become-a-creator'} title={'Become a Creator'} />
|
||
</Cards>
|
||
|
||
### Available everywhere
|
||
|
||
LobeHub runs in the [browser](https://app.lobehub.com), on [macOS and Windows](/docs/usage/getting-started/get-lobehub), and on [iOS and Android](/docs/usage/getting-started/get-lobehub). One account, and your Agents, Pages, and Memory sync across all devices.
|
||
|
||
Start a research session on your laptop, continue the conversation on your phone during lunch, and pick it up on your desktop when you're back. Nothing is lost.
|
||
|
||
- **[Keyboard Shortcuts](/docs/usage/user-interface/shortcuts)**: Power users can navigate, switch conversations, and trigger actions without touching the mouse.
|
||
- **[Command Menu](/docs/usage/user-interface/command-menu)**: Press a key and search everything: Agents, conversations, settings, actions. All from one place.
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/getting-started/get-lobehub'} title={'Get LobeHub'} />
|
||
|
||
<Card href={'/docs/usage/user-interface/shortcuts'} title={'Keyboard Shortcuts'} />
|
||
|
||
<Card href={'/docs/usage/user-interface/command-menu'} title={'Command Menu'} />
|
||
</Cards>
|
||
|
||
---
|
||
|
||
<Callout type="info">
|
||
For self-hosting, visit the [Self-Hosting Guide](/docs/self-hosting/start). For developer
|
||
resources, see the [Developer Guide](/docs/development/start).
|
||
</Callout>
|
||
|
||
<Cards>
|
||
<Card href={'/docs/usage/migrate-from-local-database'} title={'Migrate from v1.x to v2.x'} />
|
||
|
||
<Card href={'/docs/usage/help'} title={'Help & Support'} />
|
||
</Cards>
|