> 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/advanced-basic/agent-channels.md).
# Channel
When you configure an agent in Cherry Studio, such as a "research report bot" or "customer service assistant", if you want it**to stay in an IM group**and serve multiple people, you can use the "Channels" feature.
**channels**to [Agent](/docs/en-us/cherry-studio/preview/agent.md) **connect to an IM platform**and serve externally as a bot.
Currently supported platforms:
* Feishu / Lark (China version + international version)
* Telegram
* QQ (official bot API)
* WeChat (via iLink Bot API)
* Discord
* Slack
Example use cases:
* **Internal knowledge bot for a company**: Feishu group members @ the bot to ask questions, and it retrieves answers from the bound [Knowledge base](/docs/en-us/knowledge-base/knowledge-base.md) searching for answers
* **Personal assistant**: Telegram private chat bot that helps manage schedules, look up information, and provide translations
* **Customer service duty**: Discord bot greets users according to preset scripts
> Recommended first reading [Concepts Basics](/docs/en-us/advanced-basic/concepts-101.md) Learn about the relationship between Agents, channels, and scheduled tasks.
## Can't set it up yourself? Let AI do it for you
The channel feature involves several steps: "create a third-party platform bot → obtain credentials → fill them into Cherry Studio". For non-technical users, the barrier is relatively high.**If you're not familiar with these operations, the easiest way is to hand the task directly to an Agent with autonomous permissions (such as the built-in Cherry Claw)**.
Just describe your goal in Cherry Claw's chat window, for example:
> "Please help me set up a channel: every day at 10:00 AM, summarize the AI news from Huxiu, 36Kr, and Jiqizhixin into 5 key points and send them to my Feishu."
Cherry Claw will automatically determine what needs to be done, ask you for the necessary credentials (such as the Feishu App ID), and then help you complete channel creation and [scheduled tasks](/docs/en-us/advanced-basic/scheduled-tasks.md) configuration.
{% hint style="warning" %}
**Core prerequisites**:
* The built-in **Cherry Claw** and the agents you create yourself are both in the default state of **"Autonomous mode off + normal mode"**.
* **Before using channels (or scheduled tasks), you must manually enter the agent's edit panel and enable "Autonomous mode"**.
* After "Autonomous mode" is enabled, the underlying tool-call authorization will be taken over automatically, and the original "permission mode" setting will be hidden accordingly, so no further manual setup is needed. See [Agent](/docs/en-us/cherry-studio/preview/agent.md).
{% endhint %}
If you want to understand the details of each step, or need custom configuration, you can continue with the manual process below.
## Manual configuration process
### Prerequisites
1. A [Agent](/docs/en-us/cherry-studio/preview/agent.md)
2. enabled [API Server](/docs/en-us/advanced-basic/api-server.md)
3. **Get the bot credentials for the target IM platform**(see "Prepare credentials by platform" below; naming differs across platforms, but essentially they are the token/key officially issued by the platform to verify the bot's identity)
### Where are the channels
Open `Settings → Channels`, and you can see a list of all supported platforms:
Channel menu: each platform has a short description, and the right side is empty when not bound
### Create a channel (Feishu example)
1. Click **Feishu**
2. in the left list and click **+ Add**in the empty state on the right to bring up the add form:
Feishu channel fields
Meaning of each field:
| Field | Description |
| --------------------------------------- | ------------------------------------------------------------------------------------------------- |
| **Name** | The display name of the channel, making it easier to identify among multiple channels |
| **Bind Agent** | Select an already created Cherry Agent. If not bound, replies will use the general model |
| **App ID / App Secret** | Feishu Open Platform → Custom App → Credentials & Basic Info |
| **Encryption Key / Verification Token** | Feishu Open Platform → Event Subscriptions, optional |
| **Domain** | `Feishu (China)` / `Lark (international version)`, choose one |
| **Allowed chat ID** | Leave blank to impose no restriction; fill in to respond only in the specified group/private chat |
| **Channel permission mode** | `Inherit agent settings` / Custom. It is recommended to keep inheritance |
After filling in, click **Save**. After the channel is enabled, it will automatically start subscribing to Feishu message events.
### Prepare credentials by platform
{% tabs %}
{% tab title="Feishu / Lark" %}
**There are two integration methods; the QR-code method is recommended**:
* **QR-code registration (recommended)**: leave the Feishu channel details **App ID / App Secret**, and a QR code will pop up automatically after the channel is enabled. Scan it with the Feishu mobile app to automatically create the bot application,**no need to manually configure it in the open platform**.
* **Manual integration (advanced)**:
* In the [Open Platform](https://open.feishu.cn) create a **custom app**
* Copy **App ID** and **App Secret** into the form
* In the Feishu app's **Event Subscriptions** enable long connection (WebSocket)
* In the **Permission management** at least enable: receive one-on-one messages, receive group chat messages, send messages
{% endtab %}
{% tab title="Telegram" %}
* and [Chat with](https://t.me/BotFather) ,`/newbot` create a bot
* Copy **Bot Token**
* Just fill in the Bot Token in the form
* (optional) If you want to limit responses to certain conversations only, first add the bot to a group or private chat, then use [@get\_id\_bot](https://t.me/get_id_bot) to get the Chat ID and fill it into "Allowed session ID"
{% endtab %}
{% tab title="QQ" %}
* Apply for a bot on the QQ Open Platform → create an application → copy **App ID** and **Client Secret**
* into the form
* (optional) Allowed session ID formats:`c2c:openid`(private chat),`group:groupid`(group),`channel:channelid`(channel)
{% endtab %}
{% tab title="WeChat" %}
* **The WeChat channel is integrated via QR-code login**, with no prior registration required:
* In the channel details, click **Add WeChat account**
* A QR code will pop up after the channel is enabled
* Scan it with the WeChat mobile app to log in
* (optional) Allowed user ID format:`wxid_xxxxx`, multiple separated by commas
{% endtab %}
{% tab title="Discord" %}
* In the [Discord Developer Portal](https://discord.com/developers/applications) Create a new Application
* Generate it in the Bot subpage **Bot Token** and fill it into the form
* Invite the bot to your server
* (optional) If you want to limit the channel scope: after adding the bot to the target channel, send it `/whoami` to get the correctly formatted channel ID
{% endtab %}
{% tab title="Slack" %}
* In the [Slack API](https://api.slack.com/apps) Create a new App
* Enable **Socket Mode**, then generate **App-Level Token**(`xapp-...`) and **Bot Token**(`xoxb-...`)
* Fill both tokens into the form
* (optional) Channel scope restriction: send the bot `/whoami` to get the Slack channel ID
{% endtab %}
{% endtabs %}
### Can one Agent connect to multiple channels?
Yes. You can have the same "research assistant" Agent connect to a Feishu internal group (to report to colleagues) and your Telegram private chat (to push updates to yourself) at the same time, without interfering with each other. Each channel maintains its own conversations and permissions independently.
### Integration with scheduled tasks
* Channels can **receive** user messages to trigger Agent replies
* [scheduled tasks](/docs/en-us/advanced-basic/scheduled-tasks.md) and can **proactively** invoke the Agent and send the results to the IM platform through the channel
* Combining the two can realize a complete "daily report bot" setup
### Frequently asked questions
#### The bot doesn't respond after being added
* Confirm [API Server](/docs/en-us/advanced-basic/api-server.md) is **running** status
* Confirm that the bound Agent model provider has sufficient balance
* Check whether the "Allowed chat ID" was entered incorrectly (leave blank for no restriction)
#### Feishu bot joined the group but can't receive @ messages
* In Feishu Open Platform → Permission Management, confirm that "Get all messages in the group" is enabled
* Right-click the bot in the group → Settings, and enable "Bot can be @mentioned in this group"
#### WeChat channel disconnected
* WeChat bot integration is relatively fragile; it is recommended to prioritize Feishu / Telegram
* If unused for a long time, WeChat may log it out proactively; simply log back into iLink
{% hint style="warning" %}
Different platforms have different compliance requirements for custom bots. Before enabling it in an internal company group, please confirm that you have obtained permission from your organization / platform.
{% endhint %}
***
### 💡 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) for the official channels provided.
---
# 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/advanced-basic/agent-channels.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.