> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/cherry-studio/preview/assistants.md). # Assistant Library {% hint style="warning" %} **Naming Notes**: In Cherry Studio, there are two related but different concepts; please note the distinction: * **This page (Assistant Library)**: A **assistant preset marketplace**provides a large number of "role + prompt + parameters" templates; after adding, they will appear in the assistant list on the chat page. Essentially, it is [chat assistant](/docs/en-us/cherry-studio/preview/chat.md#zhu-shou-he-hua-ti) the source of the chat assistant. Entry: top tab `+` ➡️ Launcher ➡️ `Assistant Library`. * **Cherry Agent (agent)**: An agent system that can autonomously call tools, access files, and execute multi-step tasks, relying on local [API server](/docs/en-us/advanced-basic/api-server.md). Entry: top tab `agents`. See [Cherry Agent](/docs/en-us/cherry-studio/preview/agent.md). Both involve the word "Agent" in the UI, but **are different modules**. This page is about the Assistant Library (that is, the assistant preset marketplace). {% endhint %} ### Enter the Assistant Library Top Tab `+` ➡️ **Launcher** ➡️ Click `Assistant Library` icon, or click in the assistant list on the chat page `+ Add`.

Assistant Library — the left column is categorized by use case (with count badges), the middle column shows assistant cards in the current category, and there are four action buttons in the top right

### Find assistants in the Assistant Library * **Category filtering**: In the left column, by `My` / `Featured` and 20+ use-case categories (career, business, tools, language, office, general, writing, programming, emotions, education, creativity, academics, design, art, entertainment, life, etc.) filter; the number to the right of the category name is the number of assistants in that category * **Search**: Click in the top right corner `Search` Search by keyword across all categories * **Preview**: Click an assistant card to see that assistant's system prompt, recommended model, and parameter presets ### Add to My Assistants * Click the assistant card ➡️ select `Add to Assistant` * then you can see that assistant in the assistant list on the chat page * Added assistants will go to the top of the left column `My` categories ### Create your own assistant 1. Click in the top right corner `Create Assistant` 2. Fill in the pop-up form: * **Emoji**: Click `Select` Choose an icon for the assistant * **Name**: The name displayed in the assistant list on the chat page * **Prompt**: Determines the assistant's role and behavior; the lightning icon in the top right can be used [global default assistant model](/docs/en-us/pre-basic/settings/default-models.md) help you rewrite * **Knowledge Base**(optional): Link an existing knowledge base for automatic retrieval during conversations {% hint style="info" %} **Model binding instructions**: When creating or adding an assistant from the Assistant Library,**you do not need to and cannot choose a model in advance**. After adding the assistant to the list, you can assign or switch the specific AI model for that assistant directly in the model dropdown at the top of the chat page. {% endhint %}

Create Assistant form — Emoji / Name / Prompt (including AI optimization button) / Knowledge base

{% hint style="info" %} **Prompt rewriting**: The lightning button in the top right of the prompt input box is "AI Optimize Prompt"; clicking it will use the global default assistant model to rewrite the current content into a more structured form. {% endhint %} ### Import / Manage The four actions in the top bar on the upper right, from left to right: * **Search**: Search by keyword within the Assistant Library * **Import from External**: Import assistants shared by others from a URL or JSON file, or continuously sync via a subscription URL * **Manage Assistants**: go to `My` bulk management interface for categories (bulk delete, bulk export) * **Create Assistant**: Start creating a new assistant

External import dialog — the top supports two one-time import methods, URL / file, and the lower "Add assistant subscription" can continuously sync author updates

The "Import from External" dialog is divided into two parts: * **One-time import**: Upper `URL` / `Files` switch.`URL` mode to paste a JSON link,`Files` mode to select a JSON file locally, click `Import` to proceed * **Add Assistant Subscription**: Enter a subscription source address below (also a JSON link), click `Subscribe` then the assistants at that address will continue to sync in; when the author updates, there is no need to re-import. See [Assistant Subscription](/docs/en-us/pre-basic/data-settings/assistants-subscribe.md) ### When should you use the Assistant Library, and when should you use Cherry Agent? | Scenario | Recommended | | ------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------- | | Quick conversations with personalized "roles" (writing, translation, technical Q\&A, etc.) | **Assistant Library** | | Let AI autonomously call tools, read and write files, and complete tasks across steps | [**Cherry Agent**](/docs/en-us/cherry-studio/preview/agent.md) | | Scheduled execution, cross-platform message push | **Cherry Agent +** [**scheduled tasks**](/docs/en-us/advanced-basic/scheduled-tasks.md) **+** [**channel**](/docs/en-us/advanced-basic/agent-channels.md) | *** ### 💡 Get help and submit feedback If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) the official channels provided there. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.cherryai.com.cn/docs/en-us/cherry-studio/preview/assistants.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.