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* 📝 docs: fix outdated content across the docs site Audited docs/ against the current codebase and fixed stale content that drifted after major refactors (Clerk/NextAuth → Better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.
189 lines
8.1 KiB
Plaintext
189 lines
8.1 KiB
Plaintext
---
|
|
title: Agent
|
|
description: >-
|
|
Build a personalized AI Agent — configure its role, model, Skills, knowledge
|
|
base, and Memory in one place.
|
|
tags:
|
|
- LobeHub
|
|
- Agent
|
|
- Agent Configuration
|
|
- System Prompt
|
|
- Knowledge Base
|
|
- Memory
|
|
- Skills
|
|
---
|
|
|
|
# Agent
|
|
|
|
Every Agent in LobeHub is a persistent teammate — not a one-off conversation. Build a translation Agent that remembers your terminology, a coding Agent tuned to your stack, or a writing Agent that matches your voice. Configure the role, model, Skills, and knowledge base once; let it get smarter from there.
|
|
|
|
This guide walks you through creating and configuring your first Agent.
|
|
|
|
## What Makes an Agent
|
|
|
|
Every Agent is built from six components:
|
|
|
|
| Component | Purpose |
|
|
| ------------------ | ------------------------------------------------------------------ |
|
|
| **System Role** | The Agent's personality, expertise, and behavioral guidelines |
|
|
| **AI Model** | The LLM powering the Agent — GPT-4o, Claude, Gemini, and more |
|
|
| **Skills** | Capabilities like web search, code execution, and image generation |
|
|
| **Integrations** | MCP connections and integrations with external services |
|
|
| **Knowledge Base** | Documents and data the Agent can search and reference |
|
|
| **Memory** | Personal context the Agent learns and retains across sessions |
|
|
|
|
Start simple — a System Role and a model is all you need. Layer in Skills, Integrations, and a Knowledge Base as your work demands.
|
|
|
|
## Types of Agents
|
|
|
|
- **Built-in Agents** — Agent Builder (helps you create Agents), Pages Agent (writing), Memory Agent (manages your personal Memory)
|
|
- **Custom Agents** — Agents you create and configure for your specific workflows
|
|
- **Community Agents** — Ready-to-use Agents shared by the LobeHub community — one click to add
|
|
|
|
## Create a New Agent
|
|
|
|
Three paths to your first Agent: smart creation with Agent Builder, building one from scratch, or adding one from the Community. All three let you fine-tune every detail afterward.
|
|
|
|
### Smart Creation with Agent Builder
|
|
|
|
<Steps>
|
|
### Open Agent Builder
|
|
|
|
Click **Create Agent** in the left sidebar, or use the **Create Agent** option below the chat input.
|
|
|
|
### Describe Your Goal
|
|
|
|
On the Agent Profile page, chat with Agent Builder on the right panel. Describe what you need in plain language — Agent Builder generates the role settings, system prompt, and Skill configuration automatically.
|
|
|
|
### Review and Adjust
|
|
|
|
Review the generated configuration and adjust anything that doesn't fit.
|
|
</Steps>
|
|
|
|
|
|
|
|
### Build a Custom Agent
|
|
|
|
For full control: set the avatar, name, system prompt, model, and Integrations yourself on the Agent Profile page. Start with the system prompt — everything else follows.
|
|
|
|
### Add from the Community
|
|
|
|
The Community has thousands of ready-to-use Agents — design experts, coding helpers, copywriters, academic tutors, and more.
|
|
|
|
- Go to **Community → Agents** in the left sidebar, or scroll down the main screen to **Community Agents**.
|
|
- Open an Agent's detail page, then click **Add Agent & Chat** to start immediately.
|
|
|
|
|
|
|
|
### Connect Skills and Integrations
|
|
|
|
After creating an Agent, expand its capabilities by adding Skills and linking external services.
|
|
|
|
Go to **Agent Profile → + Add Skill** in the left sidebar.
|
|
|
|
|
|
|
|
### Edit Agent Information
|
|
|
|
Your Agent should evolve as your work does. Open a conversation, click **Agent Profile** in the left sidebar, and update anything — name, role, model, or Skills — at any time.
|
|
|
|
### Link a Knowledge Base
|
|
|
|
Attach a knowledge base so your Agent answers from your own data — docs, specs, or research — not just from general training.
|
|
|
|
In the chat interface, use the Knowledge Base button to select and attach a knowledge base.
|
|
|
|
|
|
|
|
<Callout type="info">
|
|
For more on knowledge bases, see [Resource Library](/docs/usage/getting-started/resource).
|
|
</Callout>
|
|
|
|
## Writing Effective System Prompts
|
|
|
|
The system prompt is the most important part of your Agent. It defines the Agent's expertise, behavior, and communication style. A well-written system prompt produces consistent, high-quality results.
|
|
|
|
**Example structure:**
|
|
|
|
```
|
|
You are an expert [ROLE] specializing in [DOMAIN].
|
|
|
|
Your expertise includes:
|
|
- [Specific area 1]
|
|
- [Specific area 2]
|
|
- [Specific area 3]
|
|
|
|
When responding:
|
|
- [Communication guideline 1]
|
|
- [Communication guideline 2]
|
|
- [Format preference]
|
|
```
|
|
|
|
**Tips for writing good prompts:**
|
|
|
|
- **Be specific about expertise** — "You are a senior TypeScript engineer specializing in React and performance optimization" is far more useful than "You are a coding assistant."
|
|
- **Define the communication style** — Specify tone (professional, casual), response length (concise/detailed), and format (markdown, bullet points, prose).
|
|
- **Include domain-specific guidelines** — For a legal writing Agent: "Cite relevant statutes when applicable. Flag when advice requires licensed legal counsel."
|
|
- **Start simple, iterate** — Begin with a basic prompt and refine based on the Agent's actual responses.
|
|
|
|
## Choosing the Right Model
|
|
|
|
Different models have different strengths:
|
|
|
|
| Model | Best For |
|
|
| ---------------------------- | --------------------------------------------- |
|
|
| GPT-5, Claude Sonnet 4.6 | Balanced performance, coding, analysis |
|
|
| Claude Opus 4.8, o3 | Complex reasoning, nuanced tasks |
|
|
| Gemini | Multi-modal tasks, long context |
|
|
| GPT-5 mini, Claude Haiku 4.5 | Fast responses, simple tasks, cost efficiency |
|
|
| Ollama (local) | Privacy-sensitive tasks, offline use |
|
|
|
|
Match the model to the task complexity and your budget. For Agents that handle routine tasks, a smaller model is often sufficient and faster.
|
|
|
|
## Best Practices
|
|
|
|
- **Test your prompts** — After creating an Agent, run a few sample conversations to verify it behaves as expected. Refine the system prompt based on what doesn't work.
|
|
- **One responsibility per Agent** — Specialized Agents outperform generalists. Create separate Agents for coding, writing, and research rather than one Agent for everything.
|
|
- **Update Agents as needs evolve** — Agents aren't set-and-forget. Revisit the system prompt when your workflows or requirements change.
|
|
- **Use Agent Builder for complex setups** — For Agents requiring multiple Skills and a sophisticated system prompt, let Agent Builder do the initial setup, then refine manually.
|
|
|
|
## Manage Agents
|
|
|
|
When you have many Agents and Group Chats, organizing them into Groups keeps the sidebar clean and makes switching easier.
|
|
|
|
### Create a Group
|
|
|
|
On the LobeHub homepage, open the Agent list menu and select **Add New Group**.
|
|
|
|
|
|
|
|
### Move to a Group
|
|
|
|
Select an existing Agent or Group Chat, then click **Move to Group**. You can also create new Agents or Group Chats directly inside a Group.
|
|
|
|
### Manage Groups
|
|
|
|
Go to the Agent list or Group menu and select **Manage Groups** to rename or reorder them.
|
|
|
|
### Pin Frequently Used Agents
|
|
|
|
Pin an Agent to the top of the list for quicker access. Select the Agent and choose **Pin** from the menu. Pinned Agents stay at the top.
|
|
|
|
## Create a Copy
|
|
|
|
Duplicate an Agent to explore different configurations without modifying the original. Select the Agent and choose **Create Copy** from the menu.
|
|
|
|
## Delete an Agent
|
|
|
|
Select the Agent, choose **Delete** from the menu, and confirm. The Agent will be removed.
|
|
|
|
<Cards>
|
|
<Card href={'/docs/usage/agent/agent-team'} title={'Agent Groups'} />
|
|
|
|
<Card href={'/docs/usage/agent/scheduled-task'} title={'Scheduled Tasks'} />
|
|
|
|
<Card href={'/docs/usage/getting-started/memory'} title={'Memory'} />
|
|
|
|
<Card href={'/docs/usage/community/publish-agent'} title={'Publish an Agent'} />
|
|
</Cards>
|