shen/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-03-01 08:22:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2681 from zhayujie/feat-docs

Browse Source 
feat: docs update
This commit is contained in:
zhayujie
2026-02-27 16:04:17 +08:00
committed by GitHub
parent 4cc6d5426b 6db22827f2
commit 2cb54514a4
97 changed files with 2801 additions and 1354 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
docs/agent.md
View File

@@ -23,7 +23,7 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
在后续的长期对话中，Agent会在需要的时候智能记录或检索记忆，并对自身设定、用户偏好、记忆文件等进行不断更新，总结和记录经验和教训，真正实现自主思考和不断成长。
<img width="800" src="https://cdn.link-ai.tech/doc/20260203000455.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260203000455.png" />
@@ -37,14 +37,14 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
针对操作系统的终端和文件的访问能力，是最基础和核心的工具，其他很多工具或技能都是基于基础工具进行扩展。用户可通过手机端与Agent交互，操作个人电脑或服务器上的资源：
<img width="800" src="https://cdn.link-ai.tech/doc/20260202181130.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260202181130.png" />
#### 1.2 编程能力
基于编程能力和系统访问能力，Agent可以实现从信息搜索、图片等素材生成、编码、测试、部署、Nginx配置修改、发布的 Vibecoding 全流程，通过手机端简单的一句命令完成应用的快速demo：
<img width="800" src="https://cdn.link-ai.tech/doc/20260203121008.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260203121008.png" />
@@ -53,7 +53,7 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
基于 scheduler 工具实现动态定时任务，支持 **一次性任务、固定时间间隔、Cron表达式** 三种形式，任务触发可选择**固定消息发送** 或 **Agent动态任务** 执行两种模式，有很高灵活性：
<img width="800" src="https://cdn.link-ai.tech/doc/20260202195402.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260202195402.png" />
同时你也可以通过自然语言快速查看和管理已有的定时任务。
@@ -62,7 +62,7 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
技能所需要的秘钥存储在环境变量文件中，由 `env_config` 工具进行管理，你可以通过对话的方式更新秘钥，工具内置了安全保护和脱敏策略，会严格保护秘钥安全：
<img width="800" src="https://cdn.link-ai.tech/doc/20260202234939.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260202234939.png" />
### 3. 技能系统
@@ -77,7 +77,7 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
通过 `skill-creator` 技能可以通过对话的方式快速创建技能。你可以在与Agent的写作中让他对将某个工作流程固化为技能，或者把任意接口文档和示例发送给Agent，让他直接完成对接：
<img width="800" src="https://cdn.link-ai.tech/doc/20260202202247.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260202202247.png" />
#### 3.2 搜索和图像识别
@@ -85,7 +85,7 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
- **搜索技能：** 系统内置实现了 `bocha-search`(博查搜索)的Skill，依赖环境变量 `BOCHA_SEARCH_API_KEY`，可在[控制台](https://open.bochaai.com/)进行创建，并发送给Agent完成配置
- **图像识别技能：** 实现了 `openai-image-vision` 插件，可使用 gpt-4.1-mini、gpt-4.1 等图像识别模型。依赖秘钥 `OPENAI_API_KEY`，可通过config.json或env_config工具进行维护。
<img width="800" src="https://cdn.link-ai.tech/doc/20260202213219.png">
<img width="800" src="https://cdn.link-ai.tech/doc/20260202213219.png" />
#### 3.3 三方知识库和插件
@@ -113,7 +113,7 @@ Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent
Agent可根据智能体的名称和描述进行决策，并通过 app_code 调用接口访问对应的应用/工作流，通过该技能，可以灵活访问LinkAI平台上的智能体、知识库、插件等能力，实现效果如下：
<img width="750" src="https://cdn.link-ai.tech/doc/20260202234350.png">
<img width="750" src="https://cdn.link-ai.tech/doc/20260202234350.png" />
注：需通过 `env_config` 配置 `LINKAI_API_KEY`，或在config.json中添加 `linkai_api_key` 配置。

2
docs/zh/channels/dingtalk.mdx → docs/channels/dingtalk.mdx
View File

@@ -3,8 +3,6 @@ title: 钉钉
description: 将 CowAgent 接入钉钉应用
---
# 钉钉
通过钉钉开放平台创建智能机器人应用，将 CowAgent 接入钉钉。
## 一、创建应用

2
docs/zh/channels/feishu.mdx → docs/channels/feishu.mdx
View File

@@ -3,8 +3,6 @@ title: 飞书
description: 将 CowAgent 接入飞书应用
---
# 飞书
通过自建应用将 CowAgent 接入飞书，支持 WebSocket 长连接（推荐）和 Webhook 两种事件接收模式。
## 一、创建企业自建应用

2
docs/zh/channels/web.mdx → docs/channels/web.mdx
View File

@@ -3,8 +3,6 @@ title: Web 网页
description: 通过 Web 网页端使用 CowAgent
---
# Web 网页
Web 是 CowAgent 的默认通道，启动后会自动运行 Web 控制台，通过浏览器即可与 Agent 对话。
## 配置

2
docs/zh/channels/wechatmp.mdx → docs/channels/wechatmp.mdx
View File

@@ -3,8 +3,6 @@ title: 微信公众号
description: 将 CowAgent 接入微信公众号
---
# 微信公众号
CowAgent 支持接入个人订阅号和企业服务号两种公众号类型。
| 类型 | 要求 | 特点 |

2
docs/zh/channels/wecom.mdx → docs/channels/wecom.mdx
View File

@@ -3,8 +3,6 @@ title: 企业微信
description: 将 CowAgent 接入企业微信自建应用
---
# 企业微信
通过企业微信自建应用接入 CowAgent，支持企业内部人员单聊使用。
<Note>

315
docs/docs.json
View File

@@ -3,14 +3,25 @@
"name": "CowAgent",
"description": "CowAgent - AI Super Assistant powered by LLMs, with autonomous task planning, long-term memory, skills system, and multi-channel deployment.",
"theme": "mint",
"colors": {
"primary": "#2563EB",
"light": "#60A5FA",
"dark": "#1D4ED8"
"appearance": {
"default": "light"
},
"favicon": "/images/favicon.png",
"colors": {
"primary": "#35A85B",
"light": "#4ABE6E",
"dark": "#228547"
},
"logo": {
"light": "/images/logo.jpg",
"dark": "/images/logo.jpg"
},
"favicon": "/images/favicon.ico",
"navbar": {
"links": [
{
"label": "官网",
"href": "https://cowagent.ai/"
},
{
"label": "GitHub",
"href": "https://github.com/zhayujie/chatgpt-on-wechat"
@@ -27,88 +38,282 @@
{
"language": "zh",
"default": true,
"groups": [
"tabs": [
{
"group": "开始",
"pages": [
"zh/index",
"zh/architecture"
"tab": "项目介绍",
"groups": [
{
"group": "概览",
"pages": [
"intro/index",
"intro/architecture",
"intro/features"
]
}
]
},
{
"group": "快速开始",
"pages": [
"zh/quick-start",
"zh/configuration"
"tab": "快速开始",
"groups": [
{
"group": "安装部署",
"pages": [
"guide/quick-start",
"guide/manual-install"
]
}
]
},
{
"group": "核心功能",
"pages": [
"zh/models",
"zh/skills",
"zh/memory"
"tab": "模型",
"groups": [
{
"group": "模型配置",
"pages": [
"models/index",
"models/minimax",
"models/glm",
"models/qwen",
"models/kimi",
"models/doubao",
"models/claude",
"models/gemini",
"models/openai",
"models/deepseek",
"models/linkai"
]
}
]
},
{
"group": "通道",
"pages": [
"zh/channels/web",
"zh/channels/feishu",
"zh/channels/dingtalk",
"zh/channels/wecom",
"zh/channels/wechatmp"
"tab": "工具",
"groups": [
{
"group": "工具系统",
"pages": [
"tools/index"
]
},
{
"group": "内置工具",
"pages": [
"tools/read",
"tools/write",
"tools/edit",
"tools/ls",
"tools/bash",
"tools/send",
"tools/memory",
"tools/env-config"
]
},
{
"group": "可选工具",
"pages": [
"tools/web-search",
"tools/scheduler"
]
}
]
},
{
"group": "版本",
"pages": [
"zh/releases/overview",
"zh/releases/v2.0.0"
"tab": "技能",
"groups": [
{
"group": "技能系统",
"pages": [
"skills/index",
"skills/skill-creator"
]
},
{
"group": "内置技能",
"pages": [
"skills/image-vision",
"skills/linkai-agent",
"skills/web-fetch"
]
}
]
},
{
"tab": "记忆",
"groups": [
{
"group": "记忆系统",
"pages": [
"memory"
]
}
]
},
{
"tab": "通道",
"groups": [
{
"group": "接入渠道",
"pages": [
"channels/web",
"channels/feishu",
"channels/dingtalk",
"channels/wecom",
"channels/wechatmp"
]
}
]
},
{
"tab": "版本",
"groups": [
{
"group": "发布记录",
"pages": [
"releases/overview",
"releases/v2.0.1",
"releases/v2.0.0"
]
}
]
}
]
},
{
"language": "en",
"groups": [
"tabs": [
{
"group": "Getting Started",
"pages": [
"en/index",
"en/architecture"
"tab": "Introduction",
"groups": [
{
"group": "Overview",
"pages": [
"en/intro/index",
"en/intro/architecture",
"en/intro/features"
]
}
]
},
{
"group": "Quick Start",
"pages": [
"en/quick-start",
"en/configuration"
"tab": "Get Started",
"groups": [
{
"group": "Installation",
"pages": [
"en/guide/quick-start",
"en/guide/manual-install"
]
}
]
},
{
"group": "Core Features",
"pages": [
"en/models",
"en/skills",
"en/memory"
"tab": "Models",
"groups": [
{
"group": "Model Configuration",
"pages": [
"en/models/index",
"en/models/minimax",
"en/models/glm",
"en/models/qwen",
"en/models/kimi",
"en/models/doubao",
"en/models/claude",
"en/models/gemini",
"en/models/openai",
"en/models/deepseek",
"en/models/linkai"
]
}
]
},
{
"group": "Channels",
"pages": [
"en/channels/web",
"en/channels/feishu",
"en/channels/dingtalk",
"en/channels/wecom",
"en/channels/wechatmp"
"tab": "Tools",
"groups": [
{
"group": "Tools System",
"pages": [
"en/tools/index"
]
},
{
"group": "Built-in Tools",
"pages": [
"en/tools/read",
"en/tools/write",
"en/tools/edit",
"en/tools/ls",
"en/tools/bash",
"en/tools/send",
"en/tools/memory",
"en/tools/env-config"
]
},
{
"group": "Optional Tools",
"pages": [
"en/tools/web-search",
"en/tools/scheduler"
]
}
]
},
{
"group": "Versions",
"pages": [
"en/releases/overview",
"en/releases/v2.0.0"
"tab": "Skills",
"groups": [
{
"group": "Skills System",
"pages": [
"en/skills/index",
"en/skills/skill-creator"
]
},
{
"group": "Built-in Skills",
"pages": [
"en/skills/image-vision",
"en/skills/linkai-agent",
"en/skills/web-fetch"
]
}
]
},
{
"tab": "Memory",
"groups": [
{
"group": "Memory System",
"pages": [
"en/memory"
]
}
]
},
{
"tab": "Channels",
"groups": [
{
"group": "Platforms",
"pages": [
"en/channels/web",
"en/channels/feishu",
"en/channels/dingtalk",
"en/channels/wecom",
"en/channels/wechatmp"
]
}
]
},
{
"tab": "Releases",
"groups": [
{
"group": "Release Notes",
"pages": [
"en/releases/overview",
"en/releases/v2.0.1",
"en/releases/v2.0.0"
]
}
]
}
]

93
docs/en/architecture.mdx
View File

@@ -1,93 +0,0 @@
---
title: Architecture
description: CowAgent 2.0 system architecture and core design
---
# Architecture
CowAgent 2.0 is a comprehensive upgrade from a simple chatbot to an AI super assistant, built on an Agent architecture with autonomous thinking, task planning, long-term memory, and skill extension capabilities.
## System Architecture
```
┌──────────────────────────────────────────────────────┐
│ Channels │
│ Web │ Feishu │ DingTalk │ WeCom │ WeChat MP │
└───────────────────────┬──────────────────────────────┘
│
┌───────────────────────▼──────────────────────────────┐
│ Agent Core │
│ ┌─────────────┐ ┌──────────┐ ┌───────────────────┐ │
│ │ Task Planner│ │ Memory │ │ Skills Engine │ │
│ └──────┬──────┘ └────┬─────┘ └────────┬──────────┘ │
│ │ │ │ │
│ ┌──────▼─────────────▼────────────────▼──────────┐ │
│ │ Tools │ │
│ │ File R/W │ Bash │ Browser │ Scheduler │ ... │ │
│ └────────────────────────────────────────────────┘ │
└───────────────────────┬──────────────────────────────┘
│
┌───────────────────────▼──────────────────────────────┐
│ Models │
│ OpenAI │ Claude │ Gemini │ MiniMax │ GLM │ ... │
└──────────────────────────────────────────────────────┘
```
### Core Modules
| Module | Description |
| --- | --- |
| **Channels** | Message channel layer for receiving and sending messages, supporting Web, Feishu, DingTalk, WeCom, WeChat Official Accounts, etc. |
| **Agent Core** | The intelligent agent engine, including task planning, memory system, and skills engine |
| **Tools** | Tool layer through which the Agent accesses OS resources, with 10+ built-in tools |
| **Models** | Model layer supporting unified access to major domestic and international LLMs |
## Agent Mode
When Agent mode is enabled, CowAgent operates as an autonomous intelligent agent with the following workflow:
1. **Receive Message** - Receives user input through a channel
2. **Understand Intent** - Analyzes task requirements and context
3. **Plan Task** - Breaks complex tasks into multiple steps
4. **Call Tools** - Selects appropriate tools to execute each step
5. **Update Memory** - Stores important information in long-term memory
6. **Return Result** - Sends execution results back to the user
## Workspace
The Agent workspace defaults to `~/cow`, storing system prompts, memory files, skill files, etc.:
```
~/cow/
├── system.md # Agent system prompt
├── user.md # User profile
├── memory/ # Long-term memory storage
│ ├── core.md # Core memory
│ └── daily/ # Daily memory
├── skills/ # Custom skills
│ ├── skill-1/
│ └── skill-2/
└── .env # Secret keys for skills
```
## Core Configuration
Configure Agent mode parameters in `config.json`:
```json
{
"agent": true,
"agent_workspace": "~/cow",
"agent_max_context_tokens": 40000,
"agent_max_context_turns": 30,
"agent_max_steps": 15
}
```
| Parameter | Description | Default |
| --- | --- | --- |
| `agent` | Enable Agent mode | `true` |
| `agent_workspace` | Workspace path | `~/cow` |
| `agent_max_context_tokens` | Maximum context tokens | `40000` |
| `agent_max_context_turns` | Maximum context conversation turns | `30` |
| `agent_max_steps` | Maximum tool call steps per task | `15` |

20
docs/en/channels/dingtalk.mdx
View File

@@ -1,23 +1,21 @@
---
title: DingTalk
description: Integrate CowAgent with DingTalk
description: Integrate CowAgent into DingTalk application
---
# DingTalk
Integrate CowAgent into DingTalk by creating an intelligent robot app on the DingTalk Open Platform.
Create a smart bot application on the DingTalk Open Platform to integrate CowAgent.
## 1. Create App
## 1. Create an App
1. Go to [DingTalk Developer Console](https://open-dev.dingtalk.com/fe/app#/corp/app), click **Create App**, and fill in the information
2. Add the **Bot** capability
3. Configure bot info and click **Publish**
1. Go to [DingTalk Developer Console](https://open-dev.dingtalk.com/fe/app#/corp/app), click **Create App**, fill in app information
2. Click **Add App Capability**, select **Robot** capability and add
3. Configure robot information and click **Publish**
## 2. Project Configuration
1. Get `Client ID` and `Client Secret` from **Credentials & Basic Info**
2. Add to `config.json`:
2. Fill in `config.json`:
```json
{
@@ -33,8 +31,8 @@ Create a smart bot application on the DingTalk Open Platform to integrate CowAge
pip3 install dingtalk_stream
```
4. After starting the project, go to **Event Subscription** in the DingTalk console, click **Verify Connection** — it should show "Connection successful"
4. After starting the project, go to DingTalk Developer Console **Event Subscription**, click **Connection verified, verify channel**. When "Connection successful" is displayed, configuration is complete
## 3. Usage
Chat with the bot privately or add it to a group chat to start a conversation.
Chat privately with the robot or add it to an enterprise group to start a conversation.

38
docs/en/channels/feishu.mdx
View File

@@ -1,25 +1,23 @@
---
title: Feishu (Lark)
description: Integrate CowAgent with Feishu
description: Integrate CowAgent into Feishu application
---
# Feishu (Lark)
Integrate CowAgent into Feishu by creating a custom app. Supports WebSocket (recommended, no public IP required) and Webhook event receiving modes.
Integrate CowAgent into Feishu by creating a custom app. Supports WebSocket (recommended) and Webhook event modes.
## 1. Create Enterprise Custom App
## 1. Create a Custom App
### 1.1 Create App
### Create the App
Go to [Feishu Developer Platform](https://open.feishu.cn/app/), click **Create Enterprise Custom App**, fill in the required information and create.
Go to [Feishu Open Platform](https://open.feishu.cn/app/), click **Create Custom App**, and fill in the required information.
### 1.2 Add Bot Capability
### Add Bot Capability
In **Add App Capabilities**, add **Bot** capability to the app.
In the **Add App Capabilities** menu, add the **Bot** capability.
### 1.3 Configure App Permissions
### Configure Permissions
Go to **Permission Management**, paste the following permissions, select all, and enable them:
Click **Permission Management**, paste the following permission string, select all and enable in batch:
```
im:message,im:message.group_at_msg,im:message.group_at_msg:readonly,im:message.p2p_msg,im:message.p2p_msg:readonly,im:message:send_as_bot,im:resource
@@ -27,11 +25,11 @@ im:message,im:message.group_at_msg,im:message.group_at_msg:readonly,im:message.p
## 2. Project Configuration
Get `App ID` and `App Secret` from **Credentials & Basic Info**, then add to `config.json`:
Get `App ID` and `App Secret` from **Credentials & Basic Info**, then fill in `config.json`:
<Tabs>
<Tab title="WebSocket (Recommended)">
No public IP required:
<Tab title="WebSocket Mode (Recommended)">
No public IP required. Configuration:
```json
{
@@ -44,8 +42,8 @@ Get `App ID` and `App Secret` from **Credentials & Basic Info**, then add to `co
Install dependency: `pip3 install lark-oapi`
</Tab>
<Tab title="Webhook">
Requires public IP:
<Tab title="Webhook Mode">
Requires public IP. Configuration:
```json
{
@@ -62,8 +60,8 @@ Get `App ID` and `App Secret` from **Credentials & Basic Info**, then add to `co
## 3. Configure Event Subscription
1. After starting the project, go to **Events & Callbacks** on the Feishu Open Platform, select **Long Connection** mode, and save
2. Click **Add Event**, search for "Receive Message", select "Receive Message v2.0", and confirm
3. Go to **Version Management & Release**, create a new version, and submit for release approval
1. After starting the project, go to Feishu Developer Platform **Events & Callbacks**, select **Long Connection** and save
2. Click **Add Event**, search for "Receive Message", select "Receive Message v2.0", confirm and add
3. Click **Version Management & Release**, create a version and apply for production release. After approval, you can use it
Once approved, search for the bot name in Feishu to start chatting.
Search for the bot name in Feishu to start chatting.

10
docs/en/channels/web.mdx
View File

@@ -1,11 +1,9 @@
---
title: Web
description: Use CowAgent through the Web interface
description: Use CowAgent through the web interface
---
# Web
Web is the default channel for CowAgent. A Web console starts automatically on launch, allowing you to chat with the Agent through your browser.
Web is CowAgent's default channel. The web console starts automatically after launch, allowing you to chat with the Agent through a browser.
## Configuration
@@ -19,7 +17,7 @@ Web is the default channel for CowAgent. A Web console starts automatically on l
| Parameter | Description | Default |
| --- | --- | --- |
| `channel_type` | Set to `web` | `web` |
| `web_port` | Web service listening port | `9899` |
| `web_port` | Web service listen port | `9899` |
## Usage
@@ -29,5 +27,5 @@ After starting the project, visit:
- Server: `http://<server-ip>:9899/chat`
<Note>
Ensure your server firewall and security group allow access to the configured port.
Ensure the server firewall and security group allow the corresponding port.
</Note>

14
docs/en/channels/wechatmp.mdx
View File

@@ -3,14 +3,12 @@ title: WeChat Official Account
description: Integrate CowAgent with WeChat Official Accounts
---
# WeChat Official Account
CowAgent supports both personal subscription accounts and enterprise service accounts.
| Type | Requirements | Features |
| --- | --- | --- |
| **Personal Subscription** | Available to individuals | Users must send a message to retrieve replies |
| **Enterprise Service** | Enterprise registration with verified customer service API | Can proactively push replies to users |
| **Enterprise Service** | Enterprise with verified customer service API | Can proactively push replies to users |
<Note>
Official Accounts only support server and Docker deployment. Install extended dependencies: `pip3 install -r requirements-optional.txt`
@@ -18,8 +16,6 @@ CowAgent supports both personal subscription accounts and enterprise service acc
## Personal Subscription Account
Add the following to `config.json`:
```json
{
"channel_type": "wechatmp",
@@ -36,15 +32,15 @@ Add the following to `config.json`:
1. Get parameters from [WeChat Official Account Platform](https://mp.weixin.qq.com/) under **Settings & Development → Basic Configuration → Server Configuration**
2. Enable developer secret and add server IP to the whitelist
3. Start the program (listens on port 80)
4. In the official account console, **enable server configuration** with URL format `http://{HOST}/wx`
4. Enable server configuration with URL format `http://{HOST}/wx`
## Enterprise Service Account
The setup is largely identical to the subscription account, with these differences:
Same setup with these differences:
1. Register an enterprise service account and complete WeChat verification, ensure **Customer Service API** permission is granted
1. Register an enterprise service account with verified **Customer Service API** permission
2. Set `"channel_type": "wechatmp_service"` in `config.json`
3. Replies can be proactively pushed to users without them having to manually retrieve them
3. Replies can be proactively pushed to users
```json
{

44
docs/en/channels/wecom.mdx
View File

@@ -1,31 +1,31 @@
---
title: WeCom
description: Integrate CowAgent with WeCom (WeChat Work) custom app
description: Integrate CowAgent into WeCom enterprise app
---
# WeCom (WeChat Work)
Integrate CowAgent through a WeCom custom application for internal team messaging.
Integrate CowAgent into WeCom through a custom enterprise app, supporting one-on-one chat for internal employees.
<Note>
WeCom only supports Docker deployment or server-based Python deployment, not local running mode.
WeCom only supports Docker deployment or server Python deployment. Local run mode is not supported.
</Note>
## 1. Prerequisites
- A server with a public IP
- A WeCom account (individuals can register but cannot be verified)
- For verified WeCom accounts, a domain registered to the same entity
Required resources:
## 2. Create a WeCom App
1. A server with public IP
2. A registered WeCom account (individual registration is possible, but cannot be certified)
3. Certified WeCom requires a domain with corresponding entity filing
1. In the [WeCom Admin Console](https://work.weixin.qq.com/wework_admin/frame#profile), go to **My Enterprise** to get the **Corp ID**
2. Go to **App Management**, create a new app, and note the `AgentId` and `Secret`
3. Click **Set API Receive**, configure the app interface:
- URL format: `http://ip:port/wxcomapp` (verified enterprises need a registered domain)
- Generate and save the `Token` and `EncodingAESKey`
## 2. Create WeCom App
## 3. Configuration and Startup
1. Get **Corp ID** from **My Enterprise** in [WeCom Admin Console](https://work.weixin.qq.com/wework_admin/frame#profile)
2. Switch to **Application Management**, click Create Application, record `AgentId` and `Secret`
3. Click **Set API Reception**, configure application interface:
- URL format: `http://ip:port/wxcomapp` (certified enterprises must use filed domain)
- Generate random `Token` and `EncodingAESKey` and save
## 3. Configuration and Run
```json
{
@@ -41,19 +41,19 @@ Integrate CowAgent through a WeCom custom application for internal team messagin
| Parameter | Description |
| --- | --- |
| `wechatcom_corp_id` | Enterprise Corp ID |
| `wechatcomapp_token` | Token from API receive config |
| `wechatcom_corp_id` | Corp ID |
| `wechatcomapp_token` | Token from API reception config |
| `wechatcomapp_secret` | App Secret |
| `wechatcomapp_agent_id` | App AgentId |
| `wechatcomapp_aes_key` | EncodingAESKey from API receive config |
| `wechatcomapp_port` | Listening port, default 9898 |
| `wechatcomapp_aes_key` | EncodingAESKey from API reception config |
| `wechatcomapp_port` | Listen port, default 9898 |
After starting the program, save the **message server configuration** in the WeCom console, then add the server IP to **Trusted IPs**.
After starting the program, return to WeCom Admin Console to save **Message Server Configuration**, and add the server IP to **Enterprise Trusted IPs**.
<Warning>
If configuration fails: 1. Ensure the firewall and security group allow the port; 2. Verify all parameters match; 3. Verified enterprises need a registered domain.
If configuration fails: 1. Ensure firewall and security group allow the port; 2. Verify all parameters are consistent; 3. Certified enterprises must configure a filed domain.
</Warning>
## 4. Usage
Search for the app name in WeCom to start chatting. To allow external WeChat users, share the invitation QR code from **My Enterprise → WeChat Plugin**.
Search for the app name in WeCom to start chatting. To allow external WeChat users, share the invite QR code from **My Enterprise → WeChat Plugin**.

101
docs/en/configuration.mdx
View File

@@ -1,101 +0,0 @@
---
title: Configuration
description: CowAgent configuration file reference
---
# Configuration
The config template is located at `config-template.json` in the project root. Copy it to create the active `config.json`:
```bash
cp config-template.json config.json
```
## Core Settings
```json
{
"channel_type": "web",
"model": "MiniMax-M2.5",
"agent": true,
"agent_workspace": "~/cow",
"agent_max_context_tokens": 40000,
"agent_max_context_turns": 30,
"agent_max_steps": 15
}
```
| Parameter | Description | Default |
| --- | --- | --- |
| `channel_type` | Channel type | `web` |
| `model` | Model name | `MiniMax-M2.5` |
| `agent` | Enable Agent mode | `true` |
| `agent_workspace` | Agent workspace path | `~/cow` |
| `agent_max_context_tokens` | Maximum context tokens | `40000` |
| `agent_max_context_turns` | Maximum context conversation turns | `30` |
| `agent_max_steps` | Maximum tool call steps per task | `15` |
## Model API Keys
Fill in the API key for your chosen model:
```json
{
"minimax_api_key": "",
"zhipu_ai_api_key": "",
"moonshot_api_key": "",
"ark_api_key": "",
"dashscope_api_key": "",
"claude_api_key": "",
"gemini_api_key": "",
"open_ai_api_key": ""
}
```
See [Models](/en/models) for detailed model configuration.
## Voice Settings
```json
{
"speech_recognition": false,
"group_speech_recognition": false,
"voice_reply_voice": false
}
```
| Parameter | Description |
| --- | --- |
| `speech_recognition` | Enable private chat voice recognition |
| `group_speech_recognition` | Enable group chat voice recognition |
| `voice_reply_voice` | Reply to voice messages with voice |
## LinkAI Settings
```json
{
"use_linkai": false,
"linkai_api_key": "",
"linkai_app_code": ""
}
```
| Parameter | Description |
| --- | --- |
| `use_linkai` | Enable LinkAI integration |
| `linkai_api_key` | LinkAI API Key, create at [console](https://link-ai.tech/console/interface) |
| `linkai_app_code` | LinkAI app or workflow code |
## Proxy Settings
If you need a network proxy:
```json
{
"proxy": "127.0.0.1:7890"
}
```
<Tip>
For all configuration options, see the [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py) file in the project.
</Tip>

113
docs/en/guide/manual-install.mdx Normal file
View File

@@ -0,0 +1,113 @@
---
title: Manual Install
description: Deploy CowAgent manually (source code / Docker)
---
## Source Code Deployment
### 1. Clone the project
```bash
git clone https://github.com/zhayujie/chatgpt-on-wechat
cd chatgpt-on-wechat/
```
<Tip>
For network issues, use the mirror: https://gitee.com/zhayujie/chatgpt-on-wechat
</Tip>
### 2. Install dependencies
Core dependencies (required):
```bash
pip3 install -r requirements.txt
```
Optional dependencies (recommended):
```bash
pip3 install -r requirements-optional.txt
```
### 3. Configure
Copy the config template and edit:
```bash
cp config-template.json config.json
```
Fill in model API keys, channel type, and other settings in `config.json`. See the [model docs](/en/models/index) for details.
### 4. Run
**Local run:**
```bash
python3 app.py
```
By default, the Web service starts. Access `http://localhost:9899/chat` to chat.
**Background run on server:**
```bash
nohup python3 app.py & tail -f nohup.out
```
## Docker Deployment
Docker deployment does not require cloning source code or installing dependencies. For Agent mode, source deployment is recommended for broader system access.
<Note>
Requires [Docker](https://docs.docker.com/engine/install/) and docker-compose.
</Note>
**1. Download config**
```bash
wget https://cdn.link-ai.tech/code/cow/docker-compose.yml
```
Edit `docker-compose.yml` with your configuration.
**2. Start container**
```bash
sudo docker compose up -d
```
**3. View logs**
```bash
sudo docker logs -f chatgpt-on-wechat
```
## Core Configuration
```json
{
"channel_type": "web",
"model": "MiniMax-M2.5",
"agent": true,
"agent_workspace": "~/cow",
"agent_max_context_tokens": 40000,
"agent_max_context_turns": 30,
"agent_max_steps": 15
}
```
| Parameter | Description | Default |
| --- | --- | --- |
| `channel_type` | Channel type | `web` |
| `model` | Model name | `MiniMax-M2.5` |
| `agent` | Enable Agent mode | `true` |
| `agent_workspace` | Agent workspace path | `~/cow` |
| `agent_max_context_tokens` | Max context tokens | `40000` |
| `agent_max_context_turns` | Max context turns | `30` |
| `agent_max_steps` | Max decision steps per task | `15` |
<Tip>
Full configuration options are in the project [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py).
</Tip>

39
docs/en/guide/quick-start.mdx Normal file
View File

@@ -0,0 +1,39 @@
---
title: One-click Install
description: One-click install and manage CowAgent with scripts
---
The project provides scripts for one-click install, configuration, startup, and management. Script-based deployment is recommended for quick setup.
Supports Linux, macOS, and Windows. Requires Python 3.7-3.12 (3.9 recommended).
## Install Command
```bash
bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
```
The script automatically performs these steps:
1. Check Python environment (requires Python 3.7+)
2. Install required tools (git, curl, etc.)
3. Clone project to `~/chatgpt-on-wechat`
4. Install Python dependencies
5. Guided configuration for AI model and channel
6. Start service
By default, the Web service starts after installation. Access `http://localhost:9899/chat` to begin chatting.
## Management Commands
After installation, use these commands to manage the service:
| Command | Description |
| --- | --- |
| `./run.sh start` | Start service |
| `./run.sh stop` | Stop service |
| `./run.sh restart` | Restart service |
| `./run.sh status` | Check run status |
| `./run.sh logs` | View real-time logs |
| `./run.sh config` | Reconfigure |
| `./run.sh update` | Update project code |

64
docs/en/index.mdx
View File

@@ -1,64 +0,0 @@
---
title: Introduction
description: CowAgent - AI Super Assistant powered by LLMs
---
# CowAgent
**CowAgent** is an AI super assistant powered by large language models, capable of autonomous thinking and task planning, operating computers and external resources, creating and executing Skills, with long-term memory that grows with you.
CowAgent supports flexible switching between multiple models, handles multimodal messages including text, voice, images, and files, and can be integrated into web, Feishu (Lark), DingTalk, WeCom, and WeChat Official Accounts for 24/7 operation on your personal computer or server.
## Core Capabilities
<CardGroup cols={2}>
<Card title="Complex Task Planning" icon="brain">
Understands complex tasks and autonomously plans execution, continuously thinking and calling tools until the goal is achieved. Supports accessing files, terminals, browsers, scheduled tasks, and other system resources.
</Card>
<Card title="Long-term Memory" icon="database">
Automatically persists conversation memory to local files and databases, including core memory and daily memory, with keyword and vector search support.
</Card>
<Card title="Skills System" icon="puzzle-piece">
Implements a Skills creation and execution engine with multiple built-in skills, and supports custom skill development through natural language conversations.
</Card>
<Card title="Multimodal Messages" icon="image">
Supports parsing, processing, generating, and sending multiple message types including text, images, voice, and files.
</Card>
<Card title="Multiple Models" icon="microchip">
Supports OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, Kimi, Doubao, and other major model providers.
</Card>
<Card title="Multi-platform Deployment" icon="server">
Runs on local computers or servers, integrable with web, Feishu, DingTalk, WeChat Official Accounts, and WeCom.
</Card>
</CardGroup>
## Quick Experience
Run the following command in your terminal to install, configure, and start CowAgent with one click:
```bash
bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
```
After running, a Web service starts by default. Visit `http://localhost:9899/chat` to start chatting.
<CardGroup cols={2}>
<Card title="Quick Start" icon="rocket" href="/en/quick-start">
View the complete installation and setup guide
</Card>
<Card title="Architecture" icon="sitemap" href="/en/architecture">
Learn about the CowAgent system architecture
</Card>
</CardGroup>
## Disclaimer
1. This project follows the [MIT License](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/LICENSE) and is primarily for technical research and learning.
2. Token usage in Agent mode is higher than regular chat mode. Please choose models based on both effectiveness and cost. The Agent has access to the operating system — please choose deployment environments carefully.
3. The CowAgent project focuses on open-source technology development and will not participate in, authorize, or issue any cryptocurrency.
## Community
Join the open-source community by adding the assistant on WeChat:
<img width="140" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/open-community.png" />

71
docs/en/intro/architecture.mdx Normal file
View File

@@ -0,0 +1,71 @@
---
title: Architecture
description: CowAgent 2.0 system architecture and core design
---
CowAgent 2.0 has evolved from a simple chatbot into a super intelligent assistant with Agent architecture, featuring autonomous thinking, task planning, long-term memory, and skill extensibility.
## System Architecture
CowAgent's architecture consists of the following core modules:
<img src="https://cdn.link-ai.tech/doc/68ef7b212c6f791e0e74314b912149f9-sz_5847990.png" alt="CowAgent Architecture" />
### Core Modules
| Module | Description |
| --- | --- |
| **Channels** | Message channel layer for receiving and sending messages. Supports Web, Feishu, DingTalk, WeCom, WeChat Official Account, and more |
| **Agent Core** | Agent engine including task planning, memory system, and skills engine |
| **Tools** | Tool layer for Agent to access OS resources. 10+ built-in tools |
| **Models** | Model layer with unified access to mainstream LLMs |
## Agent Mode Workflow
When Agent mode is enabled, CowAgent runs as an autonomous agent with the following workflow:
1. **Receive Message** — Receive user input through channels
2. **Understand Intent** — Analyze task requirements and context
3. **Plan Task** — Break complex tasks into multiple steps
4. **Invoke Tools** — Select and execute appropriate tools for each step
5. **Update Memory** — Store important information in long-term memory
6. **Return Result** — Send execution results back to the user
## Workspace Directory Structure
The Agent workspace is located at `~/cow` by default and stores system prompts, memory files, and skill files:
```
~/cow/
├── system.md # Agent system prompt
├── user.md # User profile
├── memory/ # Long-term memory storage
│ ├── core.md # Core memory
│ └── daily/ # Daily memory
├── skills/ # Custom skills
│ ├── skill-1/
│ └── skill-2/
└── .env # Secret keys for skills
```
## Core Configuration
Configure Agent mode parameters in `config.json`:
```json
{
"agent": true,
"agent_workspace": "~/cow",
"agent_max_context_tokens": 40000,
"agent_max_context_turns": 30,
"agent_max_steps": 15
}
```
| Parameter | Description | Default |
| --- | --- | --- |
| `agent` | Enable Agent mode | `true` |
| `agent_workspace` | Workspace path | `~/cow` |
| `agent_max_context_tokens` | Max context tokens | `40000` |
| `agent_max_context_turns` | Max context turns | `30` |
| `agent_max_steps` | Max decision steps per task | `15` |

105
docs/en/intro/features.mdx Normal file
View File

@@ -0,0 +1,105 @@
---
title: Features
description: CowAgent long-term memory, task planning, and skills system in detail
---
## 1. Long-term Memory
The memory system enables the Agent to remember important information over time. The Agent proactively stores information when users share preferences, decisions, or key facts, and automatically extracts summaries when conversations reach a certain length. Memory is divided into core memory and daily memory, with hybrid retrieval supporting both keyword search and vector search.
On first launch, the Agent proactively asks the user for key information and records it in the workspace (default `~/cow`) — including agent settings, user identity, and memory files.
In subsequent long-term conversations, the Agent intelligently stores or retrieves memory as needed, continuously updating its own settings, user preferences, and memory files, summarizing experiences and lessons learned — truly achieving autonomous thinking and continuous growth.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
</Frame>
## 2. Task Planning and Tool Use
Tools are the core of how the Agent accesses operating system resources. The Agent intelligently selects and invokes tools based on task requirements, performing file read/write, command execution, scheduled tasks, and more. Built-in tools are implemented in the project's `agent/tools/` directory.
**Key tools:** file read/write/edit, Bash terminal, file send, scheduler, memory search, web search, environment config, and more.
### 2.1 Terminal and File Access
Access to the OS terminal and file system is the most fundamental and core capability. Many other tools and skills build on top of this. Users can interact with the Agent from a mobile device to operate resources on their personal computer or server:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202181130.png" width="800" />
</Frame>
### 2.2 Programming Capability
Combining programming and system access, the Agent can execute the complete **Vibecoding workflow** — from information search, asset generation, coding, testing, deployment, Nginx configuration, to publishing — all triggered by a single command from your phone:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
</Frame>
### 2.3 Scheduled Tasks
The `scheduler` tool enables dynamic scheduled tasks, supporting **one-time tasks, fixed intervals, and Cron expressions**. Tasks can be triggered as either a **fixed message send** or an **Agent dynamic task** execution:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
</Frame>
### 2.4 Environment Variable Management
Secrets required by skills are stored in an environment variable file, managed by the `env_config` tool. You can update secrets through conversation, with built-in security protection and desensitization:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
</Frame>
## 3. Skills System
The Skills system provides infinite extensibility for the Agent. Each Skill consists of a description file, execution scripts (optional), and resources (optional), describing how to complete specific types of tasks. Skills allow the Agent to follow instructions for complex workflows, invoke tools, or integrate third-party systems.
- **Built-in skills:** Located in the project's `skills/` directory, including skill creator, image recognition, LinkAI agent, web fetch, and more. Built-in skills are automatically enabled based on dependency conditions (API keys, system commands, etc.).
- **Custom skills:** Created by users through conversation, stored in the workspace (`~/cow/skills/`), capable of implementing any complex business process or third-party integration.
### 3.1 Creating Skills
The `skill-creator` skill enables rapid skill creation through conversation. You can ask the Agent to codify a workflow as a skill, or send any API documentation and examples for the Agent to complete the integration directly:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
### 3.2 Web Search and Image Recognition
- **Web search:** Built-in `web_search` tool, supports multiple search engines. Configure `BOCHA_API_KEY` or `LINKAI_API_KEY` to enable.
- **Image recognition:** Built-in `openai-image-vision` skill, supports `gpt-4.1-mini`, `gpt-4.1`, and other models. Requires `OPENAI_API_KEY`.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>
### 3.3 Third-party Knowledge Bases and Plugins
The `linkai-agent` skill makes all agents on [LinkAI](https://link-ai.tech/) available as Skills for the Agent, enabling multi-agent decision making.
Configuration: set `LINKAI_API_KEY` via `env_config`, then add agent descriptions in `skills/linkai-agent/config.json`:
```json
{
"apps": [
{
"app_code": "G7z6vKwp",
"app_name": "LinkAI Customer Support",
"app_description": "Select only when the user needs help with LinkAI platform questions"
},
{
"app_code": "SFY5x7JR",
"app_name": "Content Creator",
"app_description": "Use only when the user needs to create images or videos"
}
]
}
```
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>

68
docs/en/intro/index.mdx Normal file
View File

@@ -0,0 +1,68 @@
---
title: Introduction
description: CowAgent - AI Super Assistant powered by LLMs
---
<img src="https://cdn.link-ai.tech/doc/78c5dd674e2c828642ecc0406669fed7.png" alt="CowAgent" width="600px"/>
**CowAgent** is an AI super assistant powered by LLMs with autonomous task planning, long-term memory, skills system, multimodal messages, multiple model support, and multi-platform deployment.
CowAgent can proactively think and plan tasks, operate computers and external resources, create and execute Skills, and continuously grow with long-term memory. It supports flexible switching between multiple models, handles text, voice, images, files and other multimodal messages, and can be integrated into web, Feishu, DingTalk, WeCom, and WeChat Official Account. It runs 7x24 hours on your personal computer or server.
<Card title="GitHub" icon="github" href="https://github.com/zhayujie/chatgpt-on-wechat">
github.com/zhayujie/chatgpt-on-wechat
</Card>
## Core Capabilities
<CardGroup cols={2}>
<Card title="Autonomous Task Planning" icon="brain" href="/en/intro/architecture">
Understands complex tasks and autonomously plans execution, continuously thinking and invoking tools until goals are achieved. Supports accessing file systems, terminals, browsers, schedulers, and other system resources through tools.
</Card>
<Card title="Long-term Memory" icon="database" href="/en/memory">
Automatically persists conversation memory to local files and databases, including core memory and daily memory, with keyword and vector retrieval support.
</Card>
<Card title="Skills System" icon="puzzle-piece" href="/en/skills/index">
Implements a Skills creation and execution engine with built-in skills, and supports custom Skills development through natural language conversation.
</Card>
<Card title="Multimodal Messages" icon="image" href="/en/channels/web">
Supports parsing, processing, generating, and sending text, images, voice, files, and other message types.
</Card>
<Card title="Multiple Model Support" icon="microchip" href="/en/models/index">
Supports mainstream model providers including OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, Kimi, Doubao, and more.
</Card>
<Card title="Multi-platform Deployment" icon="server" href="/en/channels/web">
Runs on local computers or servers, integrable into web, Feishu, DingTalk, WeChat Official Account, and WeCom applications.
</Card>
</CardGroup>
## Quick Experience
Run the following command in your terminal for one-click install, configuration, and startup:
```bash
bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
```
By default, the Web service starts after running. Access `http://localhost:9899/chat` to chat in the web interface.
<CardGroup cols={2}>
<Card title="Quick Start" icon="rocket" href="/en/guide/quick-start">
Complete installation and run guide
</Card>
<Card title="Architecture" icon="sitemap" href="/en/intro/architecture">
CowAgent system architecture design
</Card>
</CardGroup>
## Disclaimer
1. This project follows the [MIT License](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/LICENSE) and is intended for technical research and learning. Users must comply with local laws, regulations, policies, and corporate bylaws. Any illegal or rights-infringing use is prohibited.
2. Agent mode consumes more tokens than normal chat mode. Choose models based on effectiveness and cost. Agent has access to the host operating system — deploy with caution.
3. CowAgent focuses on open-source development and does not participate in, authorize, or issue any cryptocurrency.
## Community
Add our assistant on WeChat to join the open-source community:
<img width="140" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/open-community.png" />

36
docs/en/memory.mdx
View File

@@ -3,17 +3,15 @@ title: Memory
description: CowAgent long-term memory system
---
# Long-term Memory
The memory system enables the Agent to remember important information over time, continuously accumulating experience, understanding user preferences, and achieving autonomous thinking and growth.
The memory system enables the Agent to remember important information over time, continuously accumulating experience, understanding user preferences, and truly achieving autonomous thinking and continuous growth.
## How It Works
The Agent proactively stores memory in these scenarios:
The Agent proactively stores memory in the following scenarios:
- **When users share important information** — Automatically identifies and stores preferences, decisions, facts, and other key information
- **When conversations reach a certain length** — Automatically extracts summaries to prevent information loss
- **When retrieval is needed** — Intelligently searches historical memory and combines it with context
- **When user shares important information** — Automatically identifies and stores preferences, decisions, facts, and other key information
- **When conversation reaches a certain length** — Automatically extracts summaries to prevent information loss
- **When retrieval is needed** — Intelligently searches historical memory, combining context for responses
## Memory Types
@@ -23,16 +21,16 @@ Stored in `~/cow/memory/core.md`, containing long-term user preferences, importa
### Daily Memory
Stored in the `~/cow/memory/daily/` directory, organized by date, recording daily conversation summaries and key events.
Stored in `~/cow/memory/daily/` directory, organized by date, recording daily conversation summaries and key events.
## First Startup
## First Launch
On first startup, the Agent proactively asks the user for key information and records it in the workspace (default `~/cow`):
On first launch, the Agent will proactively ask the user for key information and save it to the workspace (default `~/cow`):
| File | Description |
| --- | --- |
| `system.md` | Agent system prompt and behavior settings |
| `user.md` | User identity and preferences |
| `user.md` | User identity information and preferences |
| `memory/core.md` | Core memory |
| `memory/daily/` | Daily memory directory |
@@ -42,17 +40,15 @@ On first startup, the Agent proactively asks the user for key information and re
## Memory Retrieval
The memory system supports hybrid retrieval:
The memory system supports hybrid retrieval modes:
- **Keyword Search** — Matches historical memory based on keywords
- **Vector Search** — Semantic similarity search that finds related memories even with different wording
- **Keyword retrieval** — Match historical memory based on keywords
- **Vector retrieval** — Semantic similarity search, finds relevant memory even with different wording
The Agent automatically triggers memory retrieval during conversations, incorporating relevant historical information into the context.
The Agent automatically triggers memory retrieval during conversation as needed, incorporating relevant historical information into context.
## Configuration
Adjust memory-related parameters in `config.json`:
```json
{
"agent_workspace": "~/cow",
@@ -63,6 +59,6 @@ Adjust memory-related parameters in `config.json`:
| Parameter | Description | Default |
| --- | --- | --- |
| `agent_workspace` | Workspace path where memory files are stored | `~/cow` |
| `agent_max_context_tokens` | Maximum context tokens, affects short-term memory capacity | `40000` |
| `agent_max_context_turns` | Maximum context turns, older conversations are discarded when exceeded | `30` |
| `agent_workspace` | Workspace path, memory files stored under this directory | `~/cow` |
| `agent_max_context_tokens` | Max context tokens, affects short-term memory capacity | `40000` |
| `agent_max_context_turns` | Max context turns, oldest conversations discarded when exceeded | `30` |

173
docs/en/models.mdx
View File

@@ -1,173 +0,0 @@
---
title: Models
description: Supported models and configuration guide
---
# Models
CowAgent supports major LLM providers from China and worldwide. Model implementations are in the `models/` directory.
<Note>
Recommended models for Agent mode: MiniMax-M2.5, glm-5, kimi-k2.5, qwen3.5-plus, claude-sonnet-4-6, gemini-3.1-pro-preview. Choose based on effectiveness and cost.
</Note>
## Model Configuration
Set the model name and corresponding API key in `config.json`.
### MiniMax
```json
{
"model": "MiniMax-M2.5",
"minimax_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `MiniMax-M2.5`, `MiniMax-M2.1`, `MiniMax-M2.1-lightning`, `MiniMax-M2`, etc. |
| `minimax_api_key` | Create at [MiniMax Console](https://platform.minimaxi.com/user-center/basic-information/interface-key) |
### GLM (Zhipu AI)
```json
{
"model": "glm-5",
"zhipu_ai_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `glm-5`, `glm-4.7`, `glm-4-plus`, `glm-4-flash`, etc. See [model list](https://bigmodel.cn/dev/api/normal-model/glm-4) |
| `zhipu_ai_api_key` | Create at [Zhipu AI Console](https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
### Qwen (Tongyi Qianwen)
```json
{
"model": "qwen3.5-plus",
"dashscope_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `qwen3.5-plus`, `qwen3-max`, `qwen-max`, `qwen-plus`, etc. |
| `dashscope_api_key` | Create at [Bailian Console](https://bailian.console.aliyun.com/?tab=model#/api-key) |
### Kimi (Moonshot)
```json
{
"model": "kimi-k2.5",
"moonshot_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `kimi-k2.5`, `kimi-k2`, `moonshot-v1-8k`, `moonshot-v1-32k`, etc. |
| `moonshot_api_key` | Create at [Moonshot Console](https://platform.moonshot.cn/console/api-keys) |
### Doubao (ByteDance)
```json
{
"model": "doubao-seed-2-0-code-preview-260215",
"ark_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `doubao-seed-2-0-code-preview-260215`, `doubao-seed-2-0-pro-260215`, etc. |
| `ark_api_key` | Create at [Volcano Ark Console](https://console.volcengine.com/ark/region:ark+cn-beijing/apikey) |
### Claude
```json
{
"model": "claude-sonnet-4-6",
"claude_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `claude-sonnet-4-6`, `claude-opus-4-6`, `claude-sonnet-4-5`, etc. See [official models](https://docs.anthropic.com/en/docs/about-claude/models/overview) |
| `claude_api_key` | Create at [Claude Console](https://console.anthropic.com/settings/keys) |
| `claude_api_base` | Optional, defaults to `https://api.anthropic.com/v1` |
### Gemini
```json
{
"model": "gemini-3.1-pro-preview",
"gemini_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `gemini-3.1-pro-preview`, `gemini-3-flash-preview`, `gemini-2.5-pro`, etc. See [official docs](https://ai.google.dev/gemini-api/docs/models) |
| `gemini_api_key` | Create at [Google AI Studio](https://aistudio.google.com/app/apikey) |
### OpenAI
```json
{
"model": "gpt-4.1-mini",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.openai.com/v1"
}
```
| Parameter | Description |
| --- | --- |
| `model` | o-series, gpt-5.2, gpt-4.1, etc. See [model list](https://platform.openai.com/docs/models) |
| `open_ai_api_key` | Create at [OpenAI Platform](https://platform.openai.com/api-keys) |
| `open_ai_api_base` | Optional, modify to use third-party proxy |
### DeepSeek
```json
{
"model": "deepseek-chat",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.deepseek.com/v1",
"bot_type": "chatGPT"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `deepseek-chat` (V3), `deepseek-reasoner` (R1) |
| `bot_type` | OpenAI-compatible mode, set to `chatGPT` |
## OpenAI-Compatible Access
Most models also support OpenAI-compatible access. Set `bot_type` to `chatGPT` and configure the corresponding `open_ai_api_base` and `open_ai_api_key`.
## LinkAI Platform
[LinkAI](https://link-ai.tech) allows flexible model switching with knowledge base, workflow, and plugin support.
```json
{
"use_linkai": true,
"linkai_api_key": "YOUR_API_KEY",
"linkai_app_code": "YOUR_APP_CODE"
}
```
| Parameter | Description |
| --- | --- |
| `use_linkai` | Set to `true` to enable LinkAI |
| `linkai_api_key` | Create at [console](https://link-ai.tech/console/interface) |
| `linkai_app_code` | LinkAI agent code, optional |
<Tip>
For all model names, see [`common/const.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py) in the project.
</Tip>

17
docs/en/models/claude.mdx Normal file
View File

@@ -0,0 +1,17 @@
---
title: Claude
description: Claude model configuration
---
```json
{
"model": "claude-sonnet-4-6",
"claude_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `claude-sonnet-4-6`, `claude-opus-4-6`, `claude-sonnet-4-5`, `claude-sonnet-4-0`, `claude-3-5-sonnet-latest`, etc. See [official models](https://docs.anthropic.com/en/docs/about-claude/models/overview) |
| `claude_api_key` | Create at [Claude Console](https://console.anthropic.com/settings/keys) |
| `claude_api_base` | Optional. Defaults to `https://api.anthropic.com/v1`. Change to use third-party proxy |

22
docs/en/models/deepseek.mdx Normal file
View File

@@ -0,0 +1,22 @@
---
title: DeepSeek
description: DeepSeek model configuration
---
Use OpenAI-compatible configuration:
```json
{
"model": "deepseek-chat",
"bot_type": "chatGPT",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.deepseek.com/v1"
}
```
| Parameter | Description |
| --- | --- |
| `model` | `deepseek-chat` (DeepSeek-V3), `deepseek-reasoner` (DeepSeek-R1) |
| `bot_type` | Must be `chatGPT` (OpenAI-compatible mode) |
| `open_ai_api_key` | Create at [DeepSeek Platform](https://platform.deepseek.com/api_keys) |
| `open_ai_api_base` | DeepSeek platform BASE URL |

17
docs/en/models/doubao.mdx Normal file
View File

@@ -0,0 +1,17 @@
---
title: Doubao (ByteDance)
description: Doubao (Volcano Ark) model configuration
---
```json
{
"model": "doubao-seed-2-0-code-preview-260215",
"ark_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `doubao-seed-2-0-code-preview-260215`, `doubao-seed-2-0-pro-260215`, `doubao-seed-2-0-lite-260215`, etc. |
| `ark_api_key` | Create at [Volcano Ark Console](https://console.volcengine.com/ark/region:ark+cn-beijing/apikey) |
| `ark_base_url` | Optional. Defaults to `https://ark.cn-beijing.volces.com/api/v3` |

16
docs/en/models/gemini.mdx Normal file
View File

@@ -0,0 +1,16 @@
---
title: Gemini
description: Google Gemini model configuration
---
```json
{
"model": "gemini-3.1-pro-preview",
"gemini_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `gemini-3.1-pro-preview`, `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-2.5-pro`, `gemini-2.0-flash`, etc. See [official docs](https://ai.google.dev/gemini-api/docs/models) |
| `gemini_api_key` | Create at [Google AI Studio](https://aistudio.google.com/app/apikey) |

27
docs/en/models/glm.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: GLM (Zhipu AI)
description: Zhipu AI GLM model configuration
---
```json
{
"model": "glm-5",
"zhipu_ai_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `glm-5`, `glm-4.7`, `glm-4-plus`, `glm-4-flash`, `glm-4-air`, etc. See [model codes](https://bigmodel.cn/dev/api/normal-model/glm-4) |
| `zhipu_ai_api_key` | Create at [Zhipu AI Console](https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
OpenAI-compatible configuration is also supported:
```json
{
"bot_type": "chatGPT",
"model": "glm-5",
"open_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
"open_ai_api_key": "YOUR_API_KEY"
}
```

55
docs/en/models/index.mdx Normal file
View File

@@ -0,0 +1,55 @@
---
title: Models Overview
description: Supported models and recommended choices for CowAgent
---
CowAgent supports mainstream LLMs from domestic and international providers. Model interfaces are implemented in the project's `models/` directory.
<Note>
For Agent mode, the following models are recommended based on quality and cost: MiniMax-M2.5, glm-5, kimi-k2.5, qwen3.5-plus, claude-sonnet-4-6, gemini-3.1-pro-preview
</Note>
## Configuration
Configure the model name and API key in `config.json` according to your chosen model. Each model also supports OpenAI-compatible access by setting `bot_type` to `chatGPT` and configuring `open_ai_api_base` and `open_ai_api_key`.
You can also use the [LinkAI](https://link-ai.tech) platform interface to flexibly switch between multiple models with support for knowledge base, workflows, and other Agent capabilities.
## Supported Models
<CardGroup cols={2}>
<Card title="MiniMax" href="/en/models/minimax">
MiniMax-M2.5 and other series models
</Card>
<Card title="GLM (Zhipu AI)" href="/en/models/glm">
glm-5, glm-4.7 and other series models
</Card>
<Card title="Qwen (Tongyi Qianwen)" href="/en/models/qwen">
qwen3.5-plus, qwen3-max and more
</Card>
<Card title="Kimi" href="/en/models/kimi">
kimi-k2.5, kimi-k2 and more
</Card>
<Card title="Doubao (ByteDance)" href="/en/models/doubao">
doubao-seed series models
</Card>
<Card title="Claude" href="/en/models/claude">
claude-sonnet-4-6 and more
</Card>
<Card title="Gemini" href="/en/models/gemini">
gemini-3.1-pro-preview and more
</Card>
<Card title="OpenAI" href="/en/models/openai">
gpt-4.1, o-series and more
</Card>
<Card title="DeepSeek" href="/en/models/deepseek">
deepseek-chat, deepseek-reasoner
</Card>
<Card title="LinkAI" href="/en/models/linkai">
Unified multi-model interface + knowledge base
</Card>
</CardGroup>
<Tip>
For a full list of model names, refer to the project's [`common/const.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py) file.
</Tip>

27
docs/en/models/kimi.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: Kimi (Moonshot)
description: Kimi (Moonshot) model configuration
---
```json
{
"model": "kimi-k2.5",
"moonshot_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `kimi-k2.5`, `kimi-k2`, `moonshot-v1-8k`, `moonshot-v1-32k`, `moonshot-v1-128k` |
| `moonshot_api_key` | Create at [Moonshot Console](https://platform.moonshot.cn/console/api-keys) |
OpenAI-compatible configuration is also supported:
```json
{
"bot_type": "chatGPT",
"model": "kimi-k2.5",
"open_ai_api_base": "https://api.moonshot.cn/v1",
"open_ai_api_key": "YOUR_API_KEY"
}
```

23
docs/en/models/linkai.mdx Normal file
View File

@@ -0,0 +1,23 @@
---
title: LinkAI
description: Unified access to multiple models via LinkAI platform
---
The [LinkAI](https://link-ai.tech) platform lets you flexibly switch between OpenAI, Claude, Gemini, DeepSeek, Qwen, Kimi, and other models, with support for knowledge base, workflows, plugins, and other Agent capabilities.
```json
{
"use_linkai": true,
"linkai_api_key": "YOUR_API_KEY",
"linkai_app_code": "YOUR_APP_CODE"
}
```
| Parameter | Description |
| --- | --- |
| `use_linkai` | Set to `true` to enable LinkAI interface |
| `linkai_api_key` | Create at [LinkAI Console](https://link-ai.tech/console/interface) |
| `linkai_app_code` | Optional. Code of the LinkAI agent (app or workflow) |
| `model` | Leave empty to use the agent's default model. Can be switched flexibly on the platform. All models in the [model list](https://link-ai.tech/console/models) are supported |
See the [API documentation](https://docs.link-ai.tech/platform/api) for more details.

27
docs/en/models/minimax.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: MiniMax
description: MiniMax model configuration
---
```json
{
"model": "MiniMax-M2.5",
"minimax_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `MiniMax-M2.5`, `MiniMax-M2.1`, `MiniMax-M2.1-lightning`, `MiniMax-M2`, etc. |
| `minimax_api_key` | Create at [MiniMax Console](https://platform.minimaxi.com/user-center/basic-information/interface-key) |
OpenAI-compatible configuration is also supported:
```json
{
"bot_type": "chatGPT",
"model": "MiniMax-M2.5",
"open_ai_api_base": "https://api.minimaxi.com/v1",
"open_ai_api_key": "YOUR_API_KEY"
}
```

19
docs/en/models/openai.mdx Normal file
View File

@@ -0,0 +1,19 @@
---
title: OpenAI
description: OpenAI model configuration
---
```json
{
"model": "gpt-4.1-mini",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.openai.com/v1"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Matches the [model parameter](https://platform.openai.com/docs/models) of the OpenAI API. Supports o-series, gpt-5.2, gpt-5.1, gpt-4.1, etc. |
| `open_ai_api_key` | Create at [OpenAI Platform](https://platform.openai.com/api-keys) |
| `open_ai_api_base` | Optional. Change to use third-party proxy |
| `bot_type` | Not required for official OpenAI models. Set to `chatGPT` when using Claude or other non-OpenAI models via proxy |

27
docs/en/models/qwen.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: Qwen (Tongyi Qianwen)
description: Tongyi Qianwen model configuration
---
```json
{
"model": "qwen3.5-plus",
"dashscope_api_key": "YOUR_API_KEY"
}
```
| Parameter | Description |
| --- | --- |
| `model` | Options include `qwen3.5-plus`, `qwen3-max`, `qwen-max`, `qwen-plus`, `qwen-turbo`, `qwq-plus`, etc. |
| `dashscope_api_key` | Create at [Bailian Console](https://bailian.console.aliyun.com/?tab=model#/api-key). See [official docs](https://bailian.console.aliyun.com/?tab=api#/api) |
OpenAI-compatible configuration is also supported:
```json
{
"bot_type": "chatGPT",
"model": "qwen3.5-plus",
"open_ai_api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"open_ai_api_key": "YOUR_API_KEY"
}
```

120
docs/en/quick-start.mdx
View File

@@ -1,120 +0,0 @@
---
title: Quick Start
description: One-click install or manually deploy CowAgent
---
# Quick Start
CowAgent supports Linux, macOS, and Windows. It can run on personal computers or servers and requires Python 3.7 ~ 3.12 (3.9 recommended).
## One-click Install
The project provides a script for one-click installation, configuration, startup, and management:
```bash
bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
```
The script automatically:
1. Checks the Python environment (requires Python 3.7+)
2. Installs necessary tools (git, curl, etc.)
3. Clones the project to `~/chatgpt-on-wechat`
4. Installs Python dependencies
5. Guides configuration of AI models and channels
6. Starts the service
### Management Commands
After installation, use the following commands to manage the service:
| Command | Description |
| --- | --- |
| `./run.sh start` | Start service |
| `./run.sh stop` | Stop service |
| `./run.sh restart` | Restart service |
| `./run.sh status` | Check status |
| `./run.sh logs` | View live logs |
| `./run.sh config` | Reconfigure |
| `./run.sh update` | Update project |
## Manual Installation
### 1. Clone the Repository
```bash
git clone https://github.com/zhayujie/chatgpt-on-wechat
cd chatgpt-on-wechat/
```
<Tip>
For users in China, use the mirror: https://gitee.com/zhayujie/chatgpt-on-wechat
</Tip>
### 2. Install Dependencies
Core dependencies (required):
```bash
pip3 install -r requirements.txt
```
Extended dependencies (optional, recommended):
```bash
pip3 install -r requirements-optional.txt
```
### 3. Configuration
Copy the config template and edit:
```bash
cp config-template.json config.json
```
See [Configuration](/en/configuration) for detailed settings.
### 4. Run
**Local:**
```bash
python3 app.py
```
After starting, visit `http://localhost:9899/chat` to begin chatting.
**Server (background):**
```bash
nohup python3 app.py & tail -f nohup.out
```
## Docker Deployment
Docker deployment requires no source code download or dependency installation. Source code deployment is recommended in Agent mode for better system access.
<Note>
Requires [Docker](https://docs.docker.com/engine/install/) and docker-compose.
</Note>
**1. Download config file**
```bash
wget https://cdn.link-ai.tech/code/cow/docker-compose.yml
```
Edit `docker-compose.yml` to fill in required configuration.
**2. Start container**
```bash
sudo docker compose up -d
```
**3. View logs**
```bash
sudo docker logs -f chatgpt-on-wechat
```

7
docs/en/releases/overview.mdx
View File

@@ -3,13 +3,12 @@ title: Changelog
description: CowAgent version history
---
# Changelog
| Version | Date | Description |
| --- | --- | --- |
| [2.0.1](/en/releases/v2.0.1) | 2026.02.27 | Built-in Web Search tool, smart context management, multiple fixes |
| [2.0.0](/en/releases/v2.0.0) | 2026.02.03 | Full upgrade to AI super assistant |
| 1.7.6 | 2025.05.23 | Web Channel optimization, AgentMesh plugin |
| 1.7.5 | 2025.04.11 | wechatferry protocol, DeepSeek model |
| 1.7.5 | 2025.04.11 | DeepSeek model |
| 1.7.4 | 2024.12.13 | Gemini 2.0 model, Web Channel |
| 1.7.3 | 2024.10.31 | Stability improvements, database features |
| 1.7.2 | 2024.09.26 | One-click install script, o1 model |
@@ -17,8 +16,6 @@ description: CowAgent version history
| 1.6.9 | 2024.07.19 | gpt-4o-mini, Alibaba voice recognition |
| 1.6.8 | 2024.07.05 | Claude 3.5, Gemini 1.5 Pro |
| 1.6.0 | 2024.04.26 | Kimi integration, gpt-4-turbo upgrade |
| 1.5.8 | 2024.03.26 | GLM-4, Claude-3, edge-tts |
| 1.5.2 | 2023.11.10 | Feishu channel, image recognition |
| 1.5.0 | 2023.11.10 | gpt-4-turbo, dall-e-3, tts multimodal |
| 1.0.0 | 2022.12.12 | Project created, first ChatGPT integration |

74
docs/en/releases/v2.0.0.mdx
View File

@@ -3,105 +3,61 @@ title: v2.0.0
description: CowAgent 2.0 - Full upgrade from chatbot to AI super assistant
---
# CowAgent 2.0
CowAgent 2.0 is a comprehensive upgrade from a chatbot to an **AI super assistant**! It can now autonomously think and plan tasks, has long-term memory, operates computers and external resources, and creates and executes skills — truly understanding you and growing alongside you.
CowAgent 2.0 is a comprehensive upgrade from a chatbot to an **AI super assistant** — capable of autonomous thinking and task planning, long-term memory, operating computers, and creating and executing skills.
**Release Date**: 2026.02.03 | [GitHub Release](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.0)
## Key Updates
### Agent Core Capabilities
### Agent Core
- **Complex Task Planning**: Understands complex tasks and autonomously plans execution, continuously thinking and calling tools until goals are achieved, with multi-turn reasoning and context understanding
- **Long-term Memory**: Automatically persists conversation memory to local files and databases, including core memory and daily memory, with keyword and vector search support
- **Built-in System Tools**: 10+ built-in tools including file operations, Bash terminal, browser, file sending, scheduled tasks, memory management, etc.
- **Skills**: New Skill execution engine with built-in skills and support for custom skill development through natural language conversation
- **Security and Cost**: Controls Agent access security through secret key management, prompt controls, and system permissions; limits token costs through max memory turns, max context tokens, and tool execution steps
- **Complex Task Planning**: Autonomous planning with multi-turn reasoning
- **Long-term Memory**: Persistent memory with keyword and vector search
- **Built-in Tools**: 10+ tools including file ops, Bash, browser, scheduler
- **Web search**: Built-in `web_search` tool, supports multiple search engines, configure corresponding API key to use
- **Skills System**: Skill engine with built-in and custom skill support
- **Security & Cost**: Secret management, prompt controls, token limits
### Other Updates
### Other
- **Channel Improvements**: Feishu and DingTalk channels support WebSocket connections (no public IP needed), with image/file message support
- **Model Updates**: Added claude-sonnet-4-5, gemini-3-pro-preview, glm-4.7, MiniMax-M2.1, qwen3-max, and other latest models
- **Deployment**: Added one-click install, configure, run, and management script to simplify deployment
- **Channels**: Feishu/DingTalk WebSocket support, image/file messages
- **Models**: claude-sonnet-4-5, gemini-3-pro-preview, glm-4.7, MiniMax-M2.1, qwen3-max
- **Deployment**: One-click install, configure, run, and management script
## Long-term Memory System
The Agent proactively stores information when users share important details, and automatically extracts summaries when conversations reach a certain length. Supports hybrid retrieval with semantic search and vector search.
On **first startup**, the Agent proactively asks for key information and records it in the workspace (default `~/cow`) including agent settings, user identity, and memory files.
During **long-term conversations**, the Agent intelligently records and retrieves memories, continuously updating its settings, user preferences, and summarizing experiences — achieving true autonomous thinking and continuous growth.
## Long-term Memory
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
</Frame>
## Task Planning and Tool Calling
The Agent intelligently selects and calls tools based on task requirements to complete various complex operations.
### Terminal and File Access
The most fundamental tool capabilities. Users can interact with the Agent from mobile devices to operate resources on personal computers or servers:
## Task Planning & Tools
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202181130.png" width="800" />
</Frame>
### Application Programming
With programming and system access capabilities, the Agent can handle the complete **Vibecoding workflow** — from information search, asset generation, coding, testing, deployment, Nginx configuration, to publishing — all from a single mobile command.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
</Frame>
### Scheduled Tasks
Supports **one-time tasks, fixed intervals, and Cron expressions**, with two trigger modes: **fixed message sending** or **Agent dynamic task execution**:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
</Frame>
### Environment Variable Management
Manages skill-required secrets via the `env_config` tool, with conversational updates and built-in security protection and data masking:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
</Frame>
## Skills System
Each Skill consists of a description file, execution script (optional), and resources (optional), providing infinite extensibility.
### Skill Creator
Quickly create skills through conversation, codifying workflows or integrating with any third-party API:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
### Search and Image Recognition
- **Search Skill**: Built-in `bocha-search`, configure `BOCHA_SEARCH_API_KEY` to enable
- **Image Recognition**: Supports `gpt-4.1-mini`, `gpt-4.1`, etc., configure `OPENAI_API_KEY` to enable
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>
### Third-party Knowledge Bases and Plugins
The `linkai-agent` skill integrates all agents from [LinkAI](https://link-ai.tech/) as Skills, enabling multi-agent decision-making:
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>
## Contributing
After version 2.0, the project will continue upgrading Agent capabilities, expanding channels, built-in tools, and the skills system, while reducing model costs and improving security. Welcome to [submit feedback](https://github.com/zhayujie/chatgpt-on-wechat/issues) and [contribute code](https://github.com/zhayujie/chatgpt-on-wechat/pulls).
Welcome to [submit feedback](https://github.com/zhayujie/chatgpt-on-wechat/issues) and [contribute code](https://github.com/zhayujie/chatgpt-on-wechat/pulls).

36
docs/en/releases/v2.0.1.mdx Normal file
View File

@@ -0,0 +1,36 @@
---
title: v2.0.1
description: CowAgent 2.0.1 - Built-in Web Search, smart context management, multiple fixes
---
**Release Date**: 2026.02.27 | [Full Changelog](https://github.com/zhayujie/chatgpt-on-wechat/compare/2.0.0..2.0.1)
## New Features
- **Built-in Web Search tool**: Integrated web search as a built-in Agent tool, reducing decision cost ([4f0ea5d](https://github.com/zhayujie/chatgpt-on-wechat/commit/4f0ea5d7568d61db91ff69c91c429e785fd1b1c2))
- **Claude Opus 4.6 model support**: Added support for Claude Opus 4.6 model ([#2661](https://github.com/zhayujie/chatgpt-on-wechat/pull/2661))
- **WeCom image recognition**: Support image message recognition in WeCom channel ([#2667](https://github.com/zhayujie/chatgpt-on-wechat/pull/2667))
## Improvements
- **Smart context management**: Resolved chat context overflow with intelligent context trimming strategy to prevent token limits ([cea7fb7](https://github.com/zhayujie/chatgpt-on-wechat/commit/cea7fb7490c53454602bf05955a0e9f059bcf0fd), [8acf2db](https://github.com/zhayujie/chatgpt-on-wechat/commit/8acf2dbdfe713b84ad74b761b7f86674b1c1904d)) [#2663](https://github.com/zhayujie/chatgpt-on-wechat/issues/2663)
- **Runtime info dynamic update**: Automatic update of timestamps and other runtime info in system prompts via dynamic functions ([#2655](https://github.com/zhayujie/chatgpt-on-wechat/pull/2655), [#2657](https://github.com/zhayujie/chatgpt-on-wechat/pull/2657))
- **Skill prompt optimization**: Improved Skill system prompt generation, simplified tool descriptions for better Agent performance ([6c21833](https://github.com/zhayujie/chatgpt-on-wechat/commit/6c218331b1f1208ea8be6bf226936d3b556ade3e))
- **GLM custom API Base URL**: Support custom API Base URL for GLM models ([#2660](https://github.com/zhayujie/chatgpt-on-wechat/pull/2660))
- **Startup script optimization**: Improved `run.sh` script interaction and configuration flow ([#2656](https://github.com/zhayujie/chatgpt-on-wechat/pull/2656))
- **Decision step logging**: Added Agent decision step logging for debugging ([cb303e6](https://github.com/zhayujie/chatgpt-on-wechat/commit/cb303e6109c50c8dfef1f5e6c1ec47223bf3cd11))
## Bug Fixes
- **Scheduler memory loss**: Fixed memory loss caused by Scheduler dispatcher ([a77a874](https://github.com/zhayujie/chatgpt-on-wechat/commit/a77a8741b500a408c6f5c8868856fb4b018fe9db))
- **Empty tool calls & long results**: Fixed handling of empty tool calls and excessively long tool results ([0542700](https://github.com/zhayujie/chatgpt-on-wechat/commit/0542700f9091ebb08c1a56103b0f0f45f24aa621))
- **OpenAI Function Call**: Fixed function call compatibility with OpenAI models ([158c87a](https://github.com/zhayujie/chatgpt-on-wechat/commit/158c87ab8b05bae054cc1b4eacdbb64fc1062ba9))
- **Claude tool name field**: Removed extraneous tool name field from Claude model responses ([eec10cb](https://github.com/zhayujie/chatgpt-on-wechat/commit/eec10cb5db6a3d5bc12ef606606532237d2c5f6e))
- **MiniMax reasoning**: Optimized MiniMax model reasoning content handling, hidden thinking process output ([c72cda3](https://github.com/zhayujie/chatgpt-on-wechat/commit/c72cda33864bd1542012ee6e0a8bd8c6c88cb5ed), [72b1cac](https://github.com/zhayujie/chatgpt-on-wechat/commit/72b1cacea1ba0d1f3dedacbab2e088e98fd7e172))
- **GLM thinking process**: Hidden GLM model thinking process display ([72b1cac](https://github.com/zhayujie/chatgpt-on-wechat/commit/72b1cacea1ba0d1f3dedacbab2e088e98fd7e172))
- **Feishu connection & SSL**: Fixed Feishu channel SSL certificate errors and connection issues ([229b14b](https://github.com/zhayujie/chatgpt-on-wechat/commit/229b14b6fcabe7123d53cab1dea39f38dab26d6d), [8674421](https://github.com/zhayujie/chatgpt-on-wechat/commit/867442155e7f095b4f38b0856f8c1d8312b5fcf7))
- **model_type validation**: Fixed `AttributeError` caused by non-string `model_type` ([#2666](https://github.com/zhayujie/chatgpt-on-wechat/pull/2666))
## Platform Compatibility
- **Windows compatibility**: Fixed path handling, file encoding, and `os.getuid()` unavailability on Windows across multiple tool modules ([051ffd7](https://github.com/zhayujie/chatgpt-on-wechat/commit/051ffd78a372f71a967fd3259e37fe19131f83cf), [5264f7c](https://github.com/zhayujie/chatgpt-on-wechat/commit/5264f7ce18360ee4db5dcb4ebe67307977d40014))

103
docs/en/skills.mdx
View File

@@ -1,103 +0,0 @@
---
title: Skills
description: CowAgent Skills System - infinite extensibility for the Agent
---
# Skills System
The Skills system provides infinite extensibility for the Agent. Each Skill consists of a description file, an execution script (optional), and resources (optional), describing how to complete a specific type of task. Skills enable the Agent to follow instructions to complete complex workflows, call various tools, or integrate with third-party systems.
## Skill Types
### Built-in Skills
Located in the `skills/` directory of the project, automatically enabled based on dependency conditions (API keys, system commands, etc.).
| Skill | Description |
| --- | --- |
| `skill-creator` | Skill creator — create custom skills through conversation |
| `bocha-search` | Web search capability |
| `openai-image-vision` | Image recognition using OpenAI vision models |
| `linkai-agent` | LinkAI agent integration for third-party knowledge bases and plugins |
| `web-scraper` | Web page content extraction |
### Custom Skills
Created by users through conversation, stored in the workspace (`~/cow/skills/`). Custom skills can implement any complex business workflow or third-party system integration.
## Creating Skills
Use the built-in `skill-creator` to create skills through natural language conversation:
- Codify workflows into reusable skills
- Send API documentation and examples to the Agent for automatic integration
- Create customized automation pipelines
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
## Web Search
The built-in `bocha-search` skill provides web search capability:
1. Create an API Key at [Bocha Open Platform](https://open.bochaai.com/)
2. Configure `BOCHA_SEARCH_API_KEY` via the `env_config` tool or send it directly to the Agent
## Image Recognition
The `openai-image-vision` skill supports image recognition using models like `gpt-4.1-mini` and `gpt-4.1`.
Configure `OPENAI_API_KEY` via `config.json` or the `env_config` tool to enable.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>
## LinkAI Agents
The `linkai-agent` skill integrates all agents from [LinkAI](https://link-ai.tech/) as Skills, enabling multi-agent decision-making.
### Configuration
1. Configure `LINKAI_API_KEY` (via `env_config` tool or `linkai_api_key` in `config.json`)
2. Add agent descriptions in `skills/linkai-agent/config.json`:
```json
{
"apps": [
{
"app_code": "G7z6vKwp",
"app_name": "LinkAI Support",
"app_description": "Use this agent only for LinkAI platform questions"
},
{
"app_code": "SFY5x7JR",
"app_name": "Content Creator",
"app_description": "Use this agent for image or video creation"
}
]
}
```
The Agent selects the appropriate agent based on name and description, and calls the corresponding app via `app_code`.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>
## Skill File Structure
Each skill directory follows this structure:
```
skills/
├── my-skill/
│ ├── SKILL.md # Skill description and instructions
│ ├── run.py # Execution script (optional)
│ └── resources/ # Additional resources (optional)
```
<Tip>
For custom skill development, see the [Skill Creator Guide](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md).
</Tip>

33
docs/en/skills/image-vision.mdx Normal file
View File

@@ -0,0 +1,33 @@
---
title: Image Vision
description: Recognize images using OpenAI vision models
---
# openai-image-vision
Analyze image content using OpenAI's GPT-4 Vision API, understanding objects, text, colors, and other elements in images.
## Dependencies
| Dependency | Description |
| --- | --- |
| `OPENAI_API_KEY` | OpenAI API key |
| `curl`, `base64` | System commands (usually pre-installed) |
Configuration:
- Configure `OPENAI_API_KEY` via the `env_config` tool
- Or set `open_ai_api_key` in `config.json`
## Supported Models
- `gpt-4.1-mini` (recommended, cost-effective)
- `gpt-4.1`
## Usage
Once configured, send an image to the Agent to automatically trigger image recognition.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>

67
docs/en/skills/index.mdx Normal file
View File

@@ -0,0 +1,67 @@
---
title: Skills Overview
description: CowAgent skills system introduction
---
Skills provide infinite extensibility for the Agent. Each Skill consists of a description file (`SKILL.md`), execution scripts (optional), and resources (optional), describing how to accomplish specific types of tasks.
The difference between Skills and Tools: Tools are atomic operations implemented in code (e.g., file read/write, command execution), while Skills are high-level workflows based on description files that can combine multiple Tools to complete complex tasks.
## Built-in Skills
Located in the project `skills/` directory, automatically enabled based on dependency conditions:
| Skill | Description | Dependencies |
| --- | --- | --- |
| [`skill-creator`](/en/skills/skill-creator) | Create custom skills through conversation | None |
| [`openai-image-vision`](/en/skills/image-vision) | Recognize images using OpenAI vision models | `OPENAI_API_KEY` |
| [`linkai-agent`](/en/skills/linkai-agent) | Integrate LinkAI platform agents | `LINKAI_API_KEY` |
| [`web-fetch`](/en/skills/web-fetch) | Fetch web page text content | `curl` (enabled by default) |
## Custom Skills
Created by users through conversation, stored in workspace (`~/cow/skills/`), can implement any complex business process and third-party system integration.
## Skill Loading Priority
1. **Workspace skills** (highest): `~/cow/skills/`
2. **Project built-in skills** (lowest): `skills/`
Skills with the same name are overridden by priority.
## Skill File Structure
```
skills/
├── my-skill/
│ ├── SKILL.md # Skill description (frontmatter + instructions)
│ ├── scripts/ # Execution scripts (optional)
│ └── resources/ # Additional resources (optional)
```
### SKILL.md Format
```markdown
---
name: my-skill
description: Brief description of the skill
metadata:
emoji: 🔧
requires:
bins: ["curl"]
env: ["MY_API_KEY"]
primaryEnv: "MY_API_KEY"
---
# My Skill
Detailed instructions...
```
| Field | Description |
| --- | --- |
| `name` | Skill name, must match directory name |
| `description` | Skill description, Agent decides whether to invoke based on this |
| `metadata.requires.bins` | Required system commands |
| `metadata.requires.env` | Required environment variables |
| `metadata.always` | Always load (default false) |

49
docs/en/skills/linkai-agent.mdx Normal file
View File

@@ -0,0 +1,49 @@
---
title: LinkAI Agent
description: Integrate LinkAI platform multi-agent skill
---
# linkai-agent
Use agents from the [LinkAI](https://link-ai.tech/) platform as Skills for multi-agent decision-making. The Agent intelligently selects based on agent names and descriptions, calling the corresponding application or workflow via `app_code`.
## Dependencies
| Dependency | Description |
| --- | --- |
| `LINKAI_API_KEY` | LinkAI platform API key, created in [Console](https://link-ai.tech/console/interface) |
| `curl` | System command (usually pre-installed) |
Configuration:
- Configure `LINKAI_API_KEY` via the `env_config` tool
- Or set `linkai_api_key` in `config.json`
## Configure Agents
Add available agents in `skills/linkai-agent/config.json`:
```json
{
"apps": [
{
"app_code": "G7z6vKwp",
"app_name": "LinkAI Customer Support",
"app_description": "Select this assistant only when the user needs help with LinkAI platform questions"
},
{
"app_code": "SFY5x7JR",
"app_name": "Content Creator",
"app_description": "Use this assistant only when the user needs to create images or videos"
}
]
}
```
## Usage
Once configured, the Agent will automatically select the appropriate LinkAI agent based on the user's question.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>

33
docs/en/skills/skill-creator.mdx Normal file
View File

@@ -0,0 +1,33 @@
---
title: Skill Creator
description: Create custom skills through conversation
---
# skill-creator
Quickly create, install, or update skills through natural language conversation.
## Dependencies
No extra dependencies, always available.
## Usage
- Codify workflows as skills: "Create a skill from this deployment process"
- Integrate third-party APIs: "Create a skill based on this API documentation"
- Install remote skills: "Install xxx skill for me"
## Creation Flow
1. Tell the Agent what skill you want to create
2. Agent automatically generates `SKILL.md` description and execution scripts
3. Skill is saved to the workspace `~/cow/skills/` directory
4. Agent will automatically recognize and use the skill in future conversations
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
<Tip>
See the [Skill Creator documentation](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md) for details.
</Tip>

33
docs/en/skills/web-fetch.mdx Normal file
View File

@@ -0,0 +1,33 @@
---
title: Web Fetch
description: Fetch web page text content
---
# web-fetch
Use curl to fetch web pages and extract readable text content. A lightweight web access method without browser automation.
## Dependencies
| Dependency | Description |
| --- | --- |
| `curl` | System command (usually pre-installed) |
This skill has `always: true` set, enabled by default as long as the system has the `curl` command.
## Usage
Automatically invoked when the Agent needs to fetch content from a URL, no extra configuration needed.
## Comparison with browser Tool
| Feature | web-fetch (skill) | browser (tool) |
| --- | --- | --- |
| Dependencies | curl only | browser-use + playwright |
| JS rendering | Not supported | Supported |
| Page interaction | Not supported | Supports click, type, etc. |
| Best for | Static page text | Dynamic web pages |
<Tip>
For most web content retrieval scenarios, web-fetch is sufficient. Only use the browser tool when you need JS rendering or page interaction.
</Tip>

30
docs/en/tools/bash.mdx Normal file
View File

@@ -0,0 +1,30 @@
---
title: bash - Terminal
description: Execute system commands
---
# bash
Execute Bash commands in the current working directory, returns stdout and stderr. API keys configured via `env_config` are automatically injected into the environment.
## Dependencies
No extra dependencies, available by default.
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `command` | string | Yes | Command to execute |
| `timeout` | integer | No | Timeout in seconds |
## Use Cases
- Install packages and dependencies
- Run code and tests
- Deploy applications and services (Nginx config, process management, etc.)
- System administration and troubleshooting
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
</Frame>

27
docs/en/tools/browser.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: browser - Browser
description: Access and interact with web pages
---
# browser
Use a browser to access and interact with web pages, supports JavaScript-rendered dynamic pages.
## Dependencies
| Dependency | Install Command |
| --- | --- |
| `browser-use` ≥ 0.1.40 | `pip install browser-use` |
| `markdownify` | `pip install markdownify` |
| `playwright` + chromium | `pip install playwright && playwright install chromium` |
## Use Cases
- Access specific URLs to get page content
- Interact with web page elements (click, type, etc.)
- Verify deployed web pages
- Scrape dynamic content requiring JS rendering
<Note>
The browser tool has heavy dependencies. If not needed, skip installation. For lightweight web content retrieval, use the `web-fetch` skill instead.
</Note>

26
docs/en/tools/edit.mdx Normal file
View File

@@ -0,0 +1,26 @@
---
title: edit - File Edit
description: Edit files via precise text replacement
---
# edit
Edit files via precise text replacement. If `oldText` is empty, appends to the end of the file.
## Dependencies
No extra dependencies, available by default.
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | Yes | File path |
| `oldText` | string | Yes | Original text to replace (empty to append) |
| `newText` | string | Yes | Replacement text |
## Use Cases
- Modify specific parameters in configuration files
- Fix bugs in code
- Insert content at specific positions in files

38
docs/en/tools/env-config.mdx Normal file
View File

@@ -0,0 +1,38 @@
---
title: env_config - Environment
description: Manage API keys and secrets
---
# env_config
Manage environment variables (API keys and secrets) in the workspace `.env` file, with secure conversational updates. Built-in security protection and desensitization.
## Dependencies
| Dependency | Install Command |
| --- | --- |
| `python-dotenv` ≥ 1.0.0 | `pip install python-dotenv>=1.0.0` |
Included when installing optional dependencies: `pip3 install -r requirements-optional.txt`
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `action` | string | Yes | Operation type: `get`, `set`, `list`, `delete` |
| `key` | string | No | Environment variable name |
| `value` | string | No | Environment variable value (only for `set`) |
## Usage
Tell the Agent what key you need to configure, and it will automatically invoke this tool:
- "Configure my BOCHA_API_KEY"
- "Set OPENAI_API_KEY to sk-xxx"
- "Show configured environment variables"
Configured keys are automatically injected into the `bash` tool's execution environment.
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
</Frame>

50
docs/en/tools/index.mdx Normal file
View File

@@ -0,0 +1,50 @@
---
title: Tools Overview
description: CowAgent built-in tools system
---
Tools are the core capability for Agent to access operating system resources. The Agent intelligently selects and invokes tools based on task requirements, performing file operations, command execution, web search, scheduled tasks, and more. Tools are implemented in the `agent/tools/` directory.
## Built-in Tools
The following tools are available by default with no extra configuration:
<CardGroup cols={2}>
<Card title="read - File Read" icon="file" href="/en/tools/read">
Read file content, supports text, images, PDF
</Card>
<Card title="write - File Write" icon="pen" href="/en/tools/write">
Create or overwrite files
</Card>
<Card title="edit - File Edit" icon="pen-to-square" href="/en/tools/edit">
Edit files via precise text replacement
</Card>
<Card title="ls - Directory List" icon="folder-open" href="/en/tools/ls">
List directory contents
</Card>
<Card title="bash - Terminal" icon="terminal" href="/en/tools/bash">
Execute system commands
</Card>
<Card title="send - File Send" icon="paper-plane" href="/en/tools/send">
Send files or images to user
</Card>
<Card title="memory - Memory" icon="brain" href="/en/tools/memory">
Search and read long-term memory
</Card>
</CardGroup>
## Optional Tools
The following tools require additional dependencies or API key configuration:
<CardGroup cols={2}>
<Card title="env_config - Environment" icon="key" href="/en/tools/env-config">
Manage API keys and secrets
</Card>
<Card title="scheduler - Scheduler" icon="clock" href="/en/tools/scheduler">
Create and manage scheduled tasks
</Card>
<Card title="web_search - Web Search" icon="magnifying-glass" href="/en/tools/web-search">
Search the internet for real-time information
</Card>
</CardGroup>

25
docs/en/tools/ls.mdx Normal file
View File

@@ -0,0 +1,25 @@
---
title: ls - Directory List
description: List directory contents
---
# ls
List directory contents, sorted alphabetically, directories suffixed with `/`, includes hidden files.
## Dependencies
No extra dependencies, available by default.
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | Yes | Directory path, relative paths are based on workspace directory |
| `limit` | integer | No | Maximum entries to return, default 500 |
## Use Cases
- Browse project structure
- Find specific files
- Check if a directory exists

38
docs/en/tools/memory.mdx Normal file
View File

@@ -0,0 +1,38 @@
---
title: memory - Memory
description: Search and read long-term memory
---
# memory
The memory tool contains two sub-tools: `memory_search` (search memory) and `memory_get` (read memory files).
## Dependencies
No extra dependencies, available by default. Managed by the Agent Core memory system.
## memory_search
Search historical memory with hybrid keyword and vector retrieval.
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `query` | string | Yes | Search query |
## memory_get
Read the content of a specific memory file.
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | Yes | Relative path to memory file (e.g. `MEMORY.md`, `memory/2026-01-01.md`) |
| `start_line` | integer | No | Start line number |
| `end_line` | integer | No | End line number |
## How It Works
The Agent automatically invokes memory tools in these scenarios:
- When the user shares important information → stores to memory
- When historical context is needed → searches relevant memory
- When conversation reaches a certain length → extracts summary for storage

26
docs/en/tools/read.mdx Normal file
View File

@@ -0,0 +1,26 @@
---
title: read - File Read
description: Read file content
---
# read
Read file content. Supports text files, PDF files, images (returns metadata), and more.
## Dependencies
No extra dependencies, available by default.
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | Yes | File path, relative paths are based on workspace directory |
| `offset` | integer | No | Start line number (1-indexed), negative values read from the end |
| `limit` | integer | No | Number of lines to read |
## Use Cases
- View configuration files, log files
- Read code files for analysis
- Check image/video file info

42
docs/en/tools/scheduler.mdx Normal file
View File

@@ -0,0 +1,42 @@
---
title: scheduler - Scheduler
description: Create and manage scheduled tasks
---
# scheduler
Create and manage dynamic scheduled tasks with flexible scheduling and execution modes.
## Dependencies
| Dependency | Install Command |
| --- | --- |
| `croniter` ≥ 2.0.0 | `pip install croniter>=2.0.0` |
Included in core dependencies: `pip3 install -r requirements.txt`
## Scheduling Modes
| Mode | Description |
| --- | --- |
| One-time | Execute once at a specified time |
| Fixed interval | Repeat at fixed time intervals |
| Cron expression | Define complex schedules using Cron syntax |
## Execution Modes
- **Fixed message**: Send a preset message when triggered
- **Agent dynamic task**: Agent intelligently executes the task when triggered
## Usage
Create and manage scheduled tasks with natural language:
- "Send me a weather report every morning at 9 AM"
- "Check server status every 2 hours"
- "Remind me about the meeting tomorrow at 3 PM"
- "Show all scheduled tasks"
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
</Frame>

25
docs/en/tools/send.mdx Normal file
View File

@@ -0,0 +1,25 @@
---
title: send - File Send
description: Send files to user
---
# send
Send files to the user (images, videos, audio, documents, etc.), used when the user explicitly requests to send/share a file.
## Dependencies
No extra dependencies, available by default.
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | Yes | File path, can be absolute or relative to workspace |
| `message` | string | No | Accompanying message |
## Use Cases
- Send generated code or documents to the user
- Send screenshots, charts
- Share downloaded files

34
docs/en/tools/web-search.mdx Normal file
View File

@@ -0,0 +1,34 @@
---
title: web_search - Web Search
description: Search the internet for real-time information
---
# web_search
Search the internet for real-time information, news, research, and more. Supports two search backends with automatic fallback.
## Dependencies
Requires at least one search API key (configured via `env_config` tool or workspace `.env` file):
| Backend | Environment Variable | Priority | How to Get |
| --- | --- | --- | --- |
| Bocha Search | `BOCHA_API_KEY` | Primary | [Bocha Open Platform](https://open.bochaai.com/) |
| LinkAI Search | `LINKAI_API_KEY` | Fallback | [LinkAI Console](https://link-ai.tech/console/interface) |
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `query` | string | Yes | Search keywords |
| `count` | integer | No | Number of results (1-50, default 10) |
| `freshness` | string | No | Time range: `noLimit`, `oneDay`, `oneWeek`, `oneMonth`, `oneYear`, or date range like `2025-01-01..2025-02-01` |
| `summary` | boolean | No | Return page summaries (default false) |
## Use Cases
When the user asks about latest information, needs fact-checking, or real-time data, the Agent automatically invokes this tool.
<Note>
If no search API key is configured, this tool will not be loaded.
</Note>

29
docs/en/tools/write.mdx Normal file
View File

@@ -0,0 +1,29 @@
---
title: write - File Write
description: Create or overwrite files
---
# write
Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.
## Dependencies
No extra dependencies, available by default.
## Parameters
| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | Yes | File path |
| `content` | string | Yes | Content to write |
## Use Cases
- Create new code files or scripts
- Generate configuration files
- Save processing results
<Note>
Single writes should not exceed 10KB. For large files, create a skeleton first, then use the edit tool to add content in chunks.
</Note>

71
docs/zh/quick-start.mdx → docs/guide/manual-install.mdx
View File

@@ -1,44 +1,9 @@
---
title: 快速开始
description: 一键安装或手动部署 CowAgent
title: 手动安装
description: 手动部署 CowAgent（源码 / Docker）
---
# 快速开始
CowAgent 支持 Linux、macOS、Windows 操作系统，可在个人计算机及服务器上运行，需安装 Python 3.7 ~ 3.12（推荐 3.9）。
## 一键安装
项目提供了一键安装、配置、启动、管理程序的脚本，推荐使用脚本快速运行：
```bash
bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
```
脚本自动执行以下流程：
1. 检查 Python 环境（需要 Python 3.7+）
2. 安装必要工具（git、curl 等）
3. 克隆项目代码到 `~/chatgpt-on-wechat`
4. 安装 Python 依赖
5. 引导配置 AI 模型和通信渠道
6. 启动服务
### 脚本管理命令
安装完成后，可使用以下命令管理服务：
| 命令 | 说明 |
| --- | --- |
| `./run.sh start` | 启动服务 |
| `./run.sh stop` | 停止服务 |
| `./run.sh restart` | 重启服务 |
| `./run.sh status` | 查看运行状态 |
| `./run.sh logs` | 查看实时日志 |
| `./run.sh config` | 重新配置 |
| `./run.sh update` | 更新项目代码 |
## 手动安装
## 源码部署
### 1. 克隆项目代码
@@ -73,7 +38,7 @@ pip3 install -r requirements-optional.txt
cp config-template.json config.json
```
填写核心配置项，详细说明参考 [配置说明](/zh/configuration)。
在 `config.json` 中填写模型 API Key 和通道类型等配置，详细说明参考各 [模型文档](/models/minimax)。
### 4. 运行
@@ -118,3 +83,31 @@ sudo docker compose up -d
```bash
sudo docker logs -f chatgpt-on-wechat
```
## 核心配置项
```json
{
"channel_type": "web",
"model": "MiniMax-M2.5",
"agent": true,
"agent_workspace": "~/cow",
"agent_max_context_tokens": 40000,
"agent_max_context_turns": 30,
"agent_max_steps": 15
}
```
| 参数 | 说明 | 默认值 |
| --- | --- | --- |
| `channel_type` | 接入渠道类型 | `web` |
| `model` | 模型名称 | `MiniMax-M2.5` |
| `agent` | 是否启用 Agent 模式 | `true` |
| `agent_workspace` | Agent 工作空间路径 | `~/cow` |
| `agent_max_context_tokens` | 最大上下文 tokens | `40000` |
| `agent_max_context_turns` | 最大上下文记忆轮次 | `30` |
| `agent_max_steps` | 单次任务最大决策步数 | `15` |
<Tip>
全部配置项可在项目 [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py) 文件中查看。
</Tip>

39
docs/guide/quick-start.mdx Normal file
View File

@@ -0,0 +1,39 @@
---
title: 一键安装
description: 使用脚本一键安装和管理 CowAgent
---
项目提供了一键安装、配置、启动、管理程序的脚本，推荐使用脚本快速运行。
支持 Linux、macOS、Windows 操作系统，需安装 Python 3.7 ~ 3.12（推荐 3.9）。
## 安装命令
```bash
bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
```
脚本自动执行以下流程：
1. 检查 Python 环境（需要 Python 3.7+）
2. 安装必要工具（git、curl 等）
3. 克隆项目代码到 `~/chatgpt-on-wechat`
4. 安装 Python 依赖
5. 引导配置 AI 模型和通信渠道
6. 启动服务
运行后默认启动 Web 服务，访问 `http://localhost:9899/chat` 开始对话。
## 管理命令
安装完成后，可使用以下命令管理服务：
| 命令 | 说明 |
| --- | --- |
| `./run.sh start` | 启动服务 |
| `./run.sh stop` | 停止服务 |
| `./run.sh restart` | 重启服务 |
| `./run.sh status` | 查看运行状态 |
| `./run.sh logs` | 查看实时日志 |
| `./run.sh config` | 重新配置 |
| `./run.sh update` | 更新项目代码 |

BIN
docs/images/favicon.ico Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.2 KiB

BIN
docs/images/logo.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 21 KiB

26
docs/zh/architecture.mdx → docs/intro/architecture.mdx
View File

@@ -3,37 +3,13 @@ title: 项目架构
description: CowAgent 2.0 的系统架构和核心设计
---
# 项目架构
CowAgent 2.0 从简单的聊天机器人全面升级为超级智能助理，采用 Agent 架构设计，具备自主思考、规划任务、长期记忆和技能扩展等能力。
## 系统架构
CowAgent 的整体架构由以下核心模块组成：
```
┌──────────────────────────────────────────────────────┐
│ Channels │
│ Web │ Feishu │ DingTalk │ WeCom │ WeChat MP │
└───────────────────────┬──────────────────────────────┘
│
┌───────────────────────▼──────────────────────────────┐
│ Agent Core │
│ ┌─────────────┐ ┌──────────┐ ┌───────────────────┐ │
│ │ Task Planner│ │ Memory │ │ Skills Engine │ │
│ └──────┬──────┘ └────┬─────┘ └────────┬──────────┘ │
│ │ │ │ │
│ ┌──────▼─────────────▼────────────────▼──────────┐ │
│ │ Tools │ │
│ │ File R/W │ Bash │ Browser │ Scheduler │ ... │ │
│ └────────────────────────────────────────────────┘ │
└───────────────────────┬──────────────────────────────┘
│
┌───────────────────────▼──────────────────────────────┐
│ Models │
│ OpenAI │ Claude │ Gemini │ MiniMax │ GLM │ ... │
└──────────────────────────────────────────────────────┘
```
<img src="https://cdn.link-ai.tech/doc/68ef7b212c6f791e0e74314b912149f9-sz_5847990.png" alt="CowAgent Architecture" />
### 核心模块说明

105
docs/intro/features.mdx Normal file
View File

@@ -0,0 +1,105 @@
---
title: 功能介绍
description: CowAgent 长期记忆、任务规划、技能系统详细说明
---
## 1. 长期记忆
> 记忆系统让 Agent 能够长期记住重要信息。Agent 会在用户分享偏好、决策、事实等重要信息时主动存储，也会在对话达到一定长度时自动提取摘要。记忆分为核心记忆、天级记忆，支持语义搜索和向量检索的混合检索模式。
第一次启动 Agent 时，Agent 会主动询问关键信息，并记录至工作空间（默认 `~/cow`）中的智能体设定、用户身份、记忆文件中。
在后续的长期对话中，Agent 会在需要时智能记录或检索记忆，并对自身设定、用户偏好、记忆文件等进行不断更新，总结和记录经验和教训，真正实现自主思考和不断成长。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
</Frame>
## 2. 任务规划和工具调用
工具是 Agent 访问操作系统资源的核心，Agent 会根据任务需求智能选择和调用工具，完成文件读写、命令执行、定时任务等各类操作。内置工具的实现在项目的 `agent/tools/` 目录下。
**主要工具：** 文件读写编辑、Bash 终端、文件发送、定时调度、记忆搜索、联网搜索、环境配置等。
### 2.1 终端和文件访问
针对操作系统的终端和文件的访问能力，是最基础和核心的工具，其他很多工具或技能都是基于此进行扩展。用户可通过手机端与 Agent 交互，操作个人电脑或服务器上的资源：
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202181130.png" width="800" />
</Frame>
### 2.2 编程能力
基于编程能力和系统访问能力，Agent 可以实现从信息搜索、图片等素材生成、编码、测试、部署、Nginx 配置修改、发布的 **Vibecoding 全流程**，通过手机端简单的一句命令完成应用的快速 demo：
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
</Frame>
### 2.3 定时任务
基于 `scheduler` 工具实现动态定时任务，支持**一次性任务、固定时间间隔、Cron 表达式**三种形式，任务触发可选择**固定消息发送**或 **Agent 动态任务**执行两种模式：
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
</Frame>
### 2.4 环境变量管理
技能所需的秘钥存储在环境变量文件中，由 `env_config` 工具进行管理，你可以通过对话的方式更新秘钥，工具内置安全保护和脱敏策略：
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
</Frame>
## 3. 技能系统
技能系统为 Agent 提供无限的扩展性，每个 Skill 由说明文件、运行脚本（可选）、资源（可选）组成，描述如何完成特定类型的任务。通过 Skill 可以让 Agent 遵循说明完成复杂流程、调用各类工具或对接第三方系统。
- **内置技能：** 在项目的 `skills/` 目录下，包含技能创造器、图像识别、LinkAI 智能体、网页抓取等。内置 Skill 根据依赖条件（API Key、系统命令等）自动判断是否启用。
- **自定义技能：** 由用户通过对话创建，存放在工作空间中（`~/cow/skills/`），可实现任何复杂的业务流程和第三方系统对接。
### 3.1 创建技能
通过 `skill-creator` 技能可以通过对话的方式快速创建技能。你可以让 Agent 将某个工作流程固化为技能，或者把任意接口文档和示例发送给 Agent，让他直接完成对接：
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
### 3.2 搜索和图像识别
- **联网搜索：** 内置 `web_search` 工具，支持多种搜索引擎，配置 `BOCHA_API_KEY` 或 `LINKAI_API_KEY` 后启用。
- **图像识别：** 内置 `openai-image-vision` 技能，可使用 `gpt-4.1-mini`、`gpt-4.1` 等模型，依赖 `OPENAI_API_KEY`。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>
### 3.3 三方知识库和插件
`linkai-agent` 技能可以将 [LinkAI](https://link-ai.tech/) 上的所有智能体作为 Skill 交给 Agent 使用，实现多智能体决策效果。
配置方式：通过 `env_config` 配置 `LINKAI_API_KEY`，并在 `skills/linkai-agent/config.json` 中添加智能体说明：
```json
{
"apps": [
{
"app_code": "G7z6vKwp",
"app_name": "LinkAI客服助手",
"app_description": "当用户需要了解LinkAI平台相关问题时才选择该助手"
},
{
"app_code": "SFY5x7JR",
"app_name": "内容创作助手",
"app_description": "当用户需要创作图片或视频时才使用该助手"
}
]
}
```
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>

28
docs/zh/index.mdx → docs/intro/index.mdx
View File

@@ -3,31 +3,35 @@ title: 项目介绍
description: CowAgent - 基于大模型的超级AI助理
---
# CowAgent
<img src="https://cdn.link-ai.tech/doc/78c5dd674e2c828642ecc0406669fed7.png" alt="CowAgent" width="600px"/>
**CowAgent** 是基于大模型的超级AI助理，能够主动思考和任务规划、操作计算机和外部资源、创造和执行Skills、拥有长期记忆并不断成长。
CowAgent 支持灵活切换多种模型，能处理文本、语音、图片、文件等多模态消息，可接入网页、飞书、钉钉、企业微信应用、微信公众号中使用，7×24小时运行于你的个人电脑或服务器中。
<Card title="GitHub" icon="github" href="https://github.com/zhayujie/chatgpt-on-wechat">
github.com/zhayujie/chatgpt-on-wechat
</Card>
## 核心能力
<CardGroup cols={2}>
<Card title="复杂任务规划" icon="brain">
<Card title="复杂任务规划" icon="brain" href="/intro/architecture">
能够理解复杂任务并自主规划执行，持续思考和调用工具直到完成目标，支持通过工具操作访问文件、终端、浏览器、定时任务等系统资源。
</Card>
<Card title="长期记忆" icon="database">
<Card title="长期记忆" icon="database" href="/memory">
自动将对话记忆持久化至本地文件和数据库中，包括全局记忆和天级记忆，支持关键词及向量检索。
</Card>
<Card title="技能系统" icon="puzzle-piece">
<Card title="技能系统" icon="puzzle-piece" href="/skills/index">
实现了Skills创建和运行的引擎，内置多种技能，并支持通过自然语言对话完成自定义Skills开发。
</Card>
<Card title="多模态消息" icon="image">
<Card title="多模态消息" icon="image" href="/channels/web">
支持对文本、图片、语音、文件等多类型消息进行解析、处理、生成、发送等操作。
</Card>
<Card title="多模型接入" icon="microchip">
<Card title="多模型接入" icon="microchip" href="/models/index">
支持 OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, Kimi, Doubao 等国内外主流模型厂商。
</Card>
<Card title="多端部署" icon="server">
<Card title="多端部署" icon="server" href="/channels/web">
支持运行在本地计算机或服务器，可集成到网页、飞书、钉钉、微信公众号、企业微信应用中使用。
</Card>
</CardGroup>
@@ -43,20 +47,14 @@ bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
运行后默认会启动 Web 服务，通过访问 `http://localhost:9899/chat` 在网页端对话。
<CardGroup cols={2}>
<Card title="快速开始" icon="rocket" href="/zh/quick-start">
<Card title="快速开始" icon="rocket" href="/guide/quick-start">
查看完整的安装和运行指南
</Card>
<Card title="项目架构" icon="sitemap" href="/zh/architecture">
<Card title="项目架构" icon="sitemap" href="/intro/architecture">
了解 CowAgent 的系统架构设计
</Card>
</CardGroup>
## 声明
1. 本项目遵循 [MIT开源协议](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/LICENSE)，主要用于技术研究和学习，使用本项目时需遵守所在地法律法规、相关政策以及企业章程，禁止用于任何违法或侵犯他人权益的行为。
2. Agent模式下Token使用量高于普通对话模式，请根据效果及成本综合选择模型。Agent具有访问所在操作系统的能力，请谨慎选择项目部署环境。
3. CowAgent项目专注于开源技术开发，不会参与、授权或发行任何加密货币。
## 社区
添加小助手微信加入开源项目交流群：

18
docs/zh/memory.mdx → docs/memory.mdx
View File

@@ -1,19 +1,17 @@
---
title: 记忆
title: 长期记忆
description: CowAgent 的长期记忆系统
---
# 长期记忆
记忆系统让 Agent 能够长期记住重要信息，在对话中不断积累经验、理解用户偏好，真正实现自主思考和持续成长。
## 工作原理
Agent 会在以下场景主动存储记忆：
- **用户分享重要信息时** - 自动识别偏好、决策、事实等关键信息并存储
- **对话达到一定长度时** - 自动提取摘要，避免信息丢失
- **需要检索时** - 智能搜索历史记忆，结合上下文进行回答
- **用户分享重要信息时** — 自动识别偏好、决策、事实等关键信息并存储
- **对话达到一定长度时** — 自动提取摘要，避免信息丢失
- **需要检索时** — 智能搜索历史记忆，结合上下文进行回答
## 记忆类型
@@ -27,7 +25,7 @@ Agent 会在以下场景主动存储记忆：
## 首次启动
首次启动 Agent 时，Agent 会主动向用户询问关键信息，并记录至工作空间（默认 `~/cow`）中的以下文件：
首次启动 Agent 时，Agent 会主动向用户询问关键信息，并记录至工作空间（默认 `~/cow`）中：
| 文件 | 说明 |
| --- | --- |
@@ -44,15 +42,13 @@ Agent 会在以下场景主动存储记忆：
记忆系统支持混合检索模式：
- **关键词检索** - 基于关键词匹配历史记忆
- **向量检索** - 基于语义相似度进行搜索，即使表述不同也能找到相关记忆
- **关键词检索** — 基于关键词匹配历史记忆
- **向量检索** — 基于语义相似度搜索，即使表述不同也能找到相关记忆
Agent 会在对话中根据需要自动触发记忆检索，将相关历史信息纳入上下文。
## 相关配置
在 `config.json` 中可调整记忆相关参数：
```json
{
"agent_workspace": "~/cow",

17
docs/models/claude.mdx Normal file
View File

@@ -0,0 +1,17 @@
---
title: Claude
description: Claude 模型配置
---
```json
{
"model": "claude-sonnet-4-6",
"claude_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 支持 `claude-sonnet-4-6`、`claude-opus-4-6`、`claude-sonnet-4-5`、`claude-sonnet-4-0`、`claude-3-5-sonnet-latest` 等，参考 [官方模型](https://docs.anthropic.com/en/docs/about-claude/models/overview) |
| `claude_api_key` | 在 [Claude 控制台](https://console.anthropic.com/settings/keys) 创建 |
| `claude_api_base` | 可选，默认为 `https://api.anthropic.com/v1`，修改可接入第三方代理 |

22
docs/models/deepseek.mdx Normal file
View File

@@ -0,0 +1,22 @@
---
title: DeepSeek
description: DeepSeek 模型配置
---
通过 OpenAI 兼容方式接入：
```json
{
"model": "deepseek-chat",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.deepseek.com/v1",
"bot_type": "chatGPT"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | `deepseek-chat`（DeepSeek-V3）、`deepseek-reasoner`（DeepSeek-R1） |
| `bot_type` | 固定为 `chatGPT`（OpenAI 兼容方式） |
| `open_ai_api_key` | 在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 |
| `open_ai_api_base` | DeepSeek 平台 BASE URL |

19
docs/models/doubao.mdx Normal file
View File

@@ -0,0 +1,19 @@
---
title: 豆包 Doubao
description: 豆包 (火山方舟) 模型配置
---
# 豆包 (Doubao)
```json
{
"model": "doubao-seed-2-0-code-preview-260215",
"ark_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `doubao-seed-2-0-code-preview-260215`、`doubao-seed-2-0-pro-260215`、`doubao-seed-2-0-lite-260215` 等 |
| `ark_api_key` | 在 [火山方舟控制台](https://console.volcengine.com/ark/region:ark+cn-beijing/apikey) 创建 |
| `ark_base_url` | 可选，默认为 `https://ark.cn-beijing.volces.com/api/v3` |

16
docs/models/gemini.mdx Normal file
View File

@@ -0,0 +1,16 @@
---
title: Gemini
description: Google Gemini 模型配置
---
```json
{
"model": "gemini-3.1-pro-preview",
"gemini_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 支持 `gemini-3.1-pro-preview`、`gemini-3-flash-preview`、`gemini-3-pro-preview`、`gemini-2.5-pro`、`gemini-2.0-flash` 等，参考 [官方文档](https://ai.google.dev/gemini-api/docs/models) |
| `gemini_api_key` | 在 [Google AI Studio](https://aistudio.google.com/app/apikey) 创建 |

29
docs/models/glm.mdx Normal file
View File

@@ -0,0 +1,29 @@
---
title: 智谱 GLM
description: 智谱AI GLM 模型配置
---
# 智谱AI (GLM)
```json
{
"model": "glm-5",
"zhipu_ai_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `glm-5`、`glm-4.7`、`glm-4-plus`、`glm-4-flash`、`glm-4-air` 等，参考 [模型编码](https://bigmodel.cn/dev/api/normal-model/glm-4) |
| `zhipu_ai_api_key` | 在 [智谱AI 控制台](https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys) 创建 |
也支持 OpenAI 兼容方式接入：
```json
{
"bot_type": "chatGPT",
"model": "glm-5",
"open_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
"open_ai_api_key": "YOUR_API_KEY"
}
```

55
docs/models/index.mdx Normal file
View File

@@ -0,0 +1,55 @@
---
title: 模型概览
description: CowAgent 支持的模型及推荐选择
---
CowAgent 支持国内外主流厂商的大语言模型，模型接口实现在项目的 `models/` 目录下。
<Note>
Agent 模式下推荐使用以下模型，可根据效果及成本综合选择：MiniMax-M2.5、glm-5、kimi-k2.5、qwen3.5-plus、claude-sonnet-4-6、gemini-3.1-pro-preview
</Note>
## 配置方式
根据所选模型，在 `config.json` 中填写对应的模型名称和 API Key 即可。每个模型也支持 OpenAI 兼容方式接入，将 `bot_type` 设为 `chatGPT`，配置 `open_ai_api_base` 和 `open_ai_api_key`。
同时支持使用 [LinkAI](https://link-ai.tech) 平台接口，可灵活切换多种模型并支持知识库、工作流等 Agent 能力。
## 支持的模型
<CardGroup cols={2}>
<Card title="MiniMax" href="/models/minimax">
MiniMax-M2.5 等系列模型
</Card>
<Card title="智谱 GLM" href="/models/glm">
glm-5、glm-4.7 等系列模型
</Card>
<Card title="通义千问 Qwen" href="/models/qwen">
qwen3.5-plus、qwen3-max 等
</Card>
<Card title="Kimi" href="/models/kimi">
kimi-k2.5、kimi-k2 等
</Card>
<Card title="豆包 Doubao" href="/models/doubao">
doubao-seed 系列模型
</Card>
<Card title="Claude" href="/models/claude">
claude-sonnet-4-6 等
</Card>
<Card title="Gemini" href="/models/gemini">
gemini-3.1-pro-preview 等
</Card>
<Card title="OpenAI" href="/models/openai">
gpt-4.1、o 系列等
</Card>
<Card title="DeepSeek" href="/models/deepseek">
deepseek-chat、deepseek-reasoner
</Card>
<Card title="LinkAI" href="/models/linkai">
多模型统一接口 + 知识库
</Card>
</CardGroup>
<Tip>
全部模型名称可参考项目 [`common/const.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py) 文件。
</Tip>

29
docs/models/kimi.mdx Normal file
View File

@@ -0,0 +1,29 @@
---
title: Kimi
description: Kimi (Moonshot) 模型配置
---
# Kimi (Moonshot)
```json
{
"model": "kimi-k2.5",
"moonshot_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `kimi-k2.5`、`kimi-k2`、`moonshot-v1-8k`、`moonshot-v1-32k`、`moonshot-v1-128k` |
| `moonshot_api_key` | 在 [Moonshot 控制台](https://platform.moonshot.cn/console/api-keys) 创建 |
也支持 OpenAI 兼容方式接入：
```json
{
"bot_type": "chatGPT",
"model": "kimi-k2.5",
"open_ai_api_base": "https://api.moonshot.cn/v1",
"open_ai_api_key": "YOUR_API_KEY"
}
```

23
docs/models/linkai.mdx Normal file
View File

@@ -0,0 +1,23 @@
---
title: LinkAI
description: 通过 LinkAI 平台统一接入多种模型
---
通过 [LinkAI](https://link-ai.tech) 平台可灵活切换 OpenAI、Claude、Gemini、DeepSeek、Qwen、Kimi 等多种模型，并支持知识库、工作流、插件等 Agent 能力。
```json
{
"use_linkai": true,
"linkai_api_key": "YOUR_API_KEY",
"linkai_app_code": "YOUR_APP_CODE"
}
```
| 参数 | 说明 |
| --- | --- |
| `use_linkai` | 设为 `true` 启用 LinkAI 接口 |
| `linkai_api_key` | 在 [控制台](https://link-ai.tech/console/interface) 创建 |
| `linkai_app_code` | LinkAI 智能体（应用或工作流）的 code，选填 |
| `model` | 留空则使用智能体默认模型，可在平台中灵活切换，[模型列表](https://link-ai.tech/console/models) 中的全部模型均可使用 |
参考 [接口文档](https://docs.link-ai.tech/platform/api) 了解更多。

27
docs/models/minimax.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: MiniMax
description: MiniMax 模型配置
---
```json
{
"model": "MiniMax-M2.5",
"minimax_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `MiniMax-M2.5`、`MiniMax-M2.1`、`MiniMax-M2.1-lightning`、`MiniMax-M2` 等 |
| `minimax_api_key` | 在 [MiniMax 控制台](https://platform.minimaxi.com/user-center/basic-information/interface-key) 创建 |
也支持 OpenAI 兼容方式接入：
```json
{
"bot_type": "chatGPT",
"model": "MiniMax-M2.5",
"open_ai_api_base": "https://api.minimaxi.com/v1",
"open_ai_api_key": "YOUR_API_KEY"
}
```

19
docs/models/openai.mdx Normal file
View File

@@ -0,0 +1,19 @@
---
title: OpenAI
description: OpenAI 模型配置
---
```json
{
"model": "gpt-4.1-mini",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.openai.com/v1"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 与 OpenAI 接口的 [model 参数](https://platform.openai.com/docs/models) 一致，支持 o 系列、gpt-5.2、gpt-5.1、gpt-4.1 等 |
| `open_ai_api_key` | 在 [OpenAI 平台](https://platform.openai.com/api-keys) 创建 |
| `open_ai_api_base` | 可选，修改可接入第三方代理接口 |
| `bot_type` | 使用 OpenAI 官方模型时无需填写。当通过代理接口使用 Claude 等非 OpenAI 模型时，设为 `chatGPT` |

29
docs/models/qwen.mdx Normal file
View File

@@ -0,0 +1,29 @@
---
title: 通义千问 Qwen
description: 通义千问模型配置
---
# 通义千问 (Qwen)
```json
{
"model": "qwen3.5-plus",
"dashscope_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `qwen3.5-plus`、`qwen3-max`、`qwen-max`、`qwen-plus`、`qwen-turbo`、`qwq-plus` 等 |
| `dashscope_api_key` | 在 [百炼控制台](https://bailian.console.aliyun.com/?tab=model#/api-key) 创建，参考 [官方文档](https://bailian.console.aliyun.com/?tab=api#/api) |
也支持 OpenAI 兼容方式接入：
```json
{
"bot_type": "chatGPT",
"model": "qwen3.5-plus",
"open_ai_api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"open_ai_api_key": "YOUR_API_KEY"
}
```

7
docs/zh/releases/overview.mdx → docs/releases/overview.mdx
View File

@@ -3,13 +3,12 @@ title: 更新日志
description: CowAgent 版本更新历史
---
# 更新日志
| 版本 | 日期 | 说明 |
| --- | --- | --- |
| [2.0.0](/zh/releases/v2.0.0) | 2026.02.03 | 全面升级为超级 Agent 助理 |
| [2.0.1](/releases/v2.0.1) | 2026.02.27 | 内置 Web Search 工具、智能上下文管理、多项修复 |
| [2.0.0](/releases/v2.0.0) | 2026.02.03 | 全面升级为超级 Agent 助理 |
| 1.7.6 | 2025.05.23 | Web Channel 优化、AgentMesh 多智能体插件 |
| 1.7.5 | 2025.04.11 | wechatferry 协议、DeepSeek 模型 |
| 1.7.5 | 2025.04.11 | DeepSeek 模型 |
| 1.7.4 | 2024.12.13 | Gemini 2.0 模型、Web Channel |
| 1.7.3 | 2024.10.31 | 稳定性提升、数据库功能 |
| 1.7.2 | 2024.09.26 | 一键安装脚本、o1 模型 |

6
docs/zh/releases/v2.0.0.mdx → docs/releases/v2.0.0.mdx
View File

@@ -3,8 +3,6 @@ title: v2.0.0
description: CowAgent 2.0 - 从聊天机器人到超级智能助理的全面升级
---
# CowAgent 2.0
CowAgent 2.0 实现了从聊天机器人到**超级智能助理**的全面升级！现在它能够主动思考和规划任务、拥有长期记忆、操作计算机和外部资源、创造和执行技能，真正理解你并和你一起成长。
**发布日期**：2026.02.03 | [GitHub Release](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.0)
@@ -85,9 +83,9 @@ Agent 根据任务需求智能选择和调用工具，完成各类复杂操作
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
### 搜索和图像识别
### 网页搜索和图像识别
- **搜索技能**：内置 `bocha-search`（博查搜索），配置 `BOCHA_SEARCH_API_KEY` 即可使用
- **网页搜索**：内置 `web_search` 工具，支持多种搜索引擎，配置对应 API Key 即可使用
- **图像识别**：支持 `gpt-4.1-mini`、`gpt-4.1` 等模型，配置 `OPENAI_API_KEY` 即可使用
<Frame>

36
docs/releases/v2.0.1.mdx Normal file
View File

@@ -0,0 +1,36 @@
---
title: v2.0.1
description: CowAgent 2.0.1 - 内置 Web Search、智能上下文管理、多项修复
---
**发布日期**：2026.02 | [Full Changelog](https://github.com/zhayujie/chatgpt-on-wechat/compare/2.0.0..2.0.1)
## 新特性
- **内置 Web Search 工具**：将网络搜索作为 Agent 内置工具集成，降低决策成本 ([4f0ea5d](https://github.com/zhayujie/chatgpt-on-wechat/commit/4f0ea5d7568d61db91ff69c91c429e785fd1b1c2))
- **Claude Opus 4.6 模型支持**：新增对 Claude Opus 4.6 模型的支持 ([#2661](https://github.com/zhayujie/chatgpt-on-wechat/pull/2661))
- **企业微信图片消息识别**：支持企业微信渠道的图片消息识别功能 ([#2667](https://github.com/zhayujie/chatgpt-on-wechat/pull/2667))
## 优化
- **智能上下文管理**：解决聊天上下文溢出问题，新增智能上下文裁剪策略，防止 token 超限 ([cea7fb7](https://github.com/zhayujie/chatgpt-on-wechat/commit/cea7fb7490c53454602bf05955a0e9f059bcf0fd), [8acf2db](https://github.com/zhayujie/chatgpt-on-wechat/commit/8acf2dbdfe713b84ad74b761b7f86674b1c1904d)) [#2663](https://github.com/zhayujie/chatgpt-on-wechat/issues/2663)
- **运行时信息动态更新**：通过动态函数方案实现系统提示词中时间戳等运行时信息的自动更新 ([#2655](https://github.com/zhayujie/chatgpt-on-wechat/pull/2655), [#2657](https://github.com/zhayujie/chatgpt-on-wechat/pull/2657))
- **Skill 提示词优化**：改进 Skill 系统提示词生成逻辑，简化工具描述，提升 Agent 表现 ([6c21833](https://github.com/zhayujie/chatgpt-on-wechat/commit/6c218331b1f1208ea8be6bf226936d3b556ade3e))
- **智谱 AI 自定义 API Base URL**：支持智谱 AI 配置自定义 API Base URL ([#2660](https://github.com/zhayujie/chatgpt-on-wechat/pull/2660))
- **启动脚本优化**：改进 `run.sh` 脚本的交互体验和配置流程 ([#2656](https://github.com/zhayujie/chatgpt-on-wechat/pull/2656))
- **决策轮次日志**：新增 Agent 决策轮次的日志记录，便于调试 ([cb303e6](https://github.com/zhayujie/chatgpt-on-wechat/commit/cb303e6109c50c8dfef1f5e6c1ec47223bf3cd11))
## 问题修复
- **定时任务记忆丢失**：修复 Scheduler 调度器导致的记忆丢失问题 ([a77a874](https://github.com/zhayujie/chatgpt-on-wechat/commit/a77a8741b500a408c6f5c8868856fb4b018fe9db))
- **空工具调用与超长结果**：修复空 tool calls 及过长工具返回结果的异常处理 ([0542700](https://github.com/zhayujie/chatgpt-on-wechat/commit/0542700f9091ebb08c1a56103b0f0f45f24aa621))
- **OpenAI Function Call**：修复 OpenAI 模型的 function call 调用兼容性问题 ([158c87a](https://github.com/zhayujie/chatgpt-on-wechat/commit/158c87ab8b05bae054cc1b4eacdbb64fc1062ba9))
- **Claude 工具名字段**：移除 Claude 模型响应中多余的 tool name 字段 ([eec10cb](https://github.com/zhayujie/chatgpt-on-wechat/commit/eec10cb5db6a3d5bc12ef606606532237d2c5f6e))
- **MiniMax 推理优化**：优化 MiniMax 模型 reasoning content 处理，隐藏思考过程输出 ([c72cda3](https://github.com/zhayujie/chatgpt-on-wechat/commit/c72cda33864bd1542012ee6e0a8bd8c6c88cb5ed), [72b1cac](https://github.com/zhayujie/chatgpt-on-wechat/commit/72b1cacea1ba0d1f3dedacbab2e088e98fd7e172))
- **智谱 AI 思考过程**：隐藏智谱 AI 模型的思考过程展示 ([72b1cac](https://github.com/zhayujie/chatgpt-on-wechat/commit/72b1cacea1ba0d1f3dedacbab2e088e98fd7e172))
- **飞书连接与证书**：修复飞书渠道的 SSL 证书错误和连接异常问题 ([229b14b](https://github.com/zhayujie/chatgpt-on-wechat/commit/229b14b6fcabe7123d53cab1dea39f38dab26d6d), [8674421](https://github.com/zhayujie/chatgpt-on-wechat/commit/867442155e7f095b4f38b0856f8c1d8312b5fcf7))
- **model_type 类型校验**：修复非字符串 `model_type` 导致的 `AttributeError` ([#2666](https://github.com/zhayujie/chatgpt-on-wechat/pull/2666))
## 平台兼容
- **Windows 兼容性适配**：修复 Windows 平台下路径处理、文件编码及 `os.getuid()` 不可用等问题，涉及多个工具模块 ([051ffd7](https://github.com/zhayujie/chatgpt-on-wechat/commit/051ffd78a372f71a967fd3259e37fe19131f83cf), [5264f7c](https://github.com/zhayujie/chatgpt-on-wechat/commit/5264f7ce18360ee4db5dcb4ebe67307977d40014))

33
docs/skills/image-vision.mdx Normal file
View File

@@ -0,0 +1,33 @@
---
title: 图像识别
description: 使用 OpenAI 视觉模型识别图片
---
# openai-image-vision
使用 OpenAI 的 GPT-4 Vision API 分析图片内容，理解图像中的物体、文字、颜色等元素。
## 依赖
| 依赖 | 说明 |
| --- | --- |
| `OPENAI_API_KEY` | OpenAI API 密钥 |
| `curl`、`base64` | 系统命令（通常已预装） |
配置方式：
- 通过 `env_config` 工具配置 `OPENAI_API_KEY`
- 或在 `config.json` 中填写 `open_ai_api_key`
## 支持的模型
- `gpt-4.1-mini`（推荐，性价比高）
- `gpt-4.1`
## 使用方式
配置完成后，向 Agent 发送图片即可自动触发图像识别。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>

67
docs/skills/index.mdx Normal file
View File

@@ -0,0 +1,67 @@
---
title: 技能概览
description: CowAgent 技能系统介绍
---
技能（Skill）为 Agent 提供无限的扩展性。每个 Skill 由说明文件（`SKILL.md`）、运行脚本（可选）、资源（可选）组成，描述如何完成特定类型的任务。
Skill 与 Tool 的区别：Tool 是由代码实现的原子操作（如读写文件、执行命令），Skill 则是基于说明文件的高级工作流，可以组合调用多个 Tool 来完成复杂任务。
## 内置技能
位于项目 `skills/` 目录下，根据依赖条件自动判断是否启用：
| 技能 | 说明 | 依赖 |
| --- | --- | --- |
| [`skill-creator`](/skills/skill-creator) | 通过对话创建自定义技能 | 无 |
| [`openai-image-vision`](/skills/image-vision) | 使用 OpenAI 视觉模型识别图片 | `OPENAI_API_KEY` |
| [`linkai-agent`](/skills/linkai-agent) | 对接 LinkAI 平台智能体 | `LINKAI_API_KEY` |
| [`web-fetch`](/skills/web-fetch) | 抓取网页文本内容 | `curl`（默认启用） |
## 自定义技能
由用户通过对话创建，存放在工作空间中（`~/cow/skills/`），可实现任何复杂的业务流程和第三方系统对接。
## 技能加载优先级
1. **工作空间技能**（最高）：`~/cow/skills/`
2. **项目内置技能**（最低）：`skills/`
同名技能按优先级覆盖。
## 技能文件结构
```
skills/
├── my-skill/
│ ├── SKILL.md # Skill description (frontmatter + instructions)
│ ├── scripts/ # Execution scripts (optional)
│ └── resources/ # Additional resources (optional)
```
### SKILL.md 格式
```markdown
---
name: my-skill
description: Brief description of the skill
metadata:
emoji: 🔧
requires:
bins: ["curl"]
env: ["MY_API_KEY"]
primaryEnv: "MY_API_KEY"
---
# My Skill
Detailed instructions...
```
| 字段 | 说明 |
| --- | --- |
| `name` | 技能名称，需与目录名一致 |
| `description` | 技能描述，Agent 据此决定是否调用 |
| `metadata.requires.bins` | 依赖的系统命令 |
| `metadata.requires.env` | 依赖的环境变量 |
| `metadata.always` | 是否始终加载（默认 false） |

49
docs/skills/linkai-agent.mdx Normal file
View File

@@ -0,0 +1,49 @@
---
title: LinkAI 智能体
description: 对接 LinkAI 平台的多智能体技能
---
# linkai-agent
将 [LinkAI](https://link-ai.tech/) 平台上的智能体作为 Skill 使用，实现多智能体决策。Agent 根据智能体的名称和描述智能选择，通过 `app_code` 调用对应的应用或工作流。
## 依赖
| 依赖 | 说明 |
| --- | --- |
| `LINKAI_API_KEY` | LinkAI 平台 API 密钥，在 [控制台](https://link-ai.tech/console/interface) 创建 |
| `curl` | 系统命令（通常已预装） |
配置方式：
- 通过 `env_config` 工具配置 `LINKAI_API_KEY`
- 或在 `config.json` 中填写 `linkai_api_key`
## 配置智能体
在 `skills/linkai-agent/config.json` 中添加可用的智能体：
```json
{
"apps": [
{
"app_code": "G7z6vKwp",
"app_name": "LinkAI客服助手",
"app_description": "当用户需要了解LinkAI平台相关问题时才选择该助手"
},
{
"app_code": "SFY5x7JR",
"app_name": "内容创作助手",
"app_description": "当用户需要创作图片或视频时才使用该助手"
}
]
}
```
## 使用方式
配置完成后，Agent 会根据用户的问题自动选择合适的 LinkAI 智能体进行回答。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>

33
docs/skills/skill-creator.mdx Normal file
View File

@@ -0,0 +1,33 @@
---
title: 创建技能
description: 通过对话创建自定义技能
---
# skill-creator
通过自然语言对话快速创建、安装或更新技能。
## 依赖
无额外依赖，始终可用。
## 使用方式
- 将工作流程固化为技能："帮我把这个部署流程创建为一个技能"
- 对接第三方 API："根据这个接口文档创建一个技能"
- 安装远程技能："帮我安装 xxx 技能"
## 创建流程
1. 告诉 Agent 你想创建的技能功能
2. Agent 自动生成 `SKILL.md` 说明文件和运行脚本
3. 技能保存到工作空间的 `~/cow/skills/` 目录
4. 后续对话中 Agent 会自动识别并使用该技能
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
<Tip>
详细开发文档可参考 [Skill 创造器说明](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md)。
</Tip>

33
docs/skills/web-fetch.mdx Normal file
View File

@@ -0,0 +1,33 @@
---
title: 网页抓取
description: 抓取网页文本内容
---
# web-fetch
使用 curl 抓取网页并提取可读文本内容，轻量级的网页访问方式，无需浏览器自动化。
## 依赖
| 依赖 | 说明 |
| --- | --- |
| `curl` | 系统命令（通常已预装） |
该技能设置了 `always: true`，只要系统有 `curl` 命令即默认启用。
## 使用方式
当 Agent 需要获取某个 URL 的网页内容时会自动调用，无需额外配置。
## 与 browser 工具的区别
| 特性 | web-fetch（技能） | browser（工具） |
| --- | --- | --- |
| 依赖 | 仅 curl | browser-use + playwright |
| JS 渲染 | 不支持 | 支持 |
| 页面交互 | 不支持 | 支持点击、输入等 |
| 适用场景 | 获取静态页面文本 | 操作动态网页 |
<Tip>
对于大多数网页内容获取场景，web-fetch 就够用了。只有需要 JS 渲染或页面交互时才需要 browser 工具。
</Tip>

30
docs/tools/bash.mdx Normal file
View File

@@ -0,0 +1,30 @@
---
title: bash - 终端
description: 执行系统命令
---
# bash
在当前工作目录执行 Bash 命令，返回 stdout 和 stderr。`env_config` 中配置的 API Key 会自动注入到环境变量中。
## 依赖
无额外依赖，默认可用。
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `command` | string | 是 | 要执行的命令 |
| `timeout` | integer | 否 | 超时时间（秒） |
## 使用场景
- 安装软件包和依赖
- 运行代码和测试
- 部署应用和服务（Nginx 配置、进程管理等）
- 系统运维和排查
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
</Frame>

27
docs/tools/browser.mdx Normal file
View File

@@ -0,0 +1,27 @@
---
title: browser - 浏览器
description: 访问和操作网页
---
# browser
使用浏览器访问和操作网页，支持 JavaScript 渲染的动态页面。
## 依赖
| 依赖 | 安装命令 |
| --- | --- |
| `browser-use` ≥ 0.1.40 | `pip install browser-use` |
| `markdownify` | `pip install markdownify` |
| `playwright` + chromium | `pip install playwright && playwright install chromium` |
## 使用场景
- 访问指定 URL 获取页面内容
- 操作网页元素（点击、输入等）
- 验证部署后的网页效果
- 抓取需要 JS 渲染的动态内容
<Note>
浏览器工具依赖较重，如不需要可不安装。轻量的网页内容获取可使用 `web-fetch` 技能。
</Note>

26
docs/tools/edit.mdx Normal file
View File

@@ -0,0 +1,26 @@
---
title: edit - 文件编辑
description: 通过精确文本替换编辑文件
---
# edit
通过精确文本替换编辑文件。如果 `oldText` 为空则追加到文件末尾。
## 依赖
无额外依赖，默认可用。
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `path` | string | 是 | 文件路径 |
| `oldText` | string | 是 | 要替换的原始文本（为空时追加到末尾） |
| `newText` | string | 是 | 替换后的文本 |
## 使用场景
- 修改配置文件中的特定参数
- 修复代码中的 bug
- 在文件指定位置插入内容

38
docs/tools/env-config.mdx Normal file
View File

@@ -0,0 +1,38 @@
---
title: env_config - 环境变量
description: 管理 API Key 等秘钥配置
---
# env_config
管理工作空间 `.env` 文件中的环境变量（API Key 等秘钥），支持通过对话安全地添加和更新。内置安全保护和脱敏策略。
## 依赖
| 依赖 | 安装命令 |
| --- | --- |
| `python-dotenv` ≥ 1.0.0 | `pip install python-dotenv>=1.0.0` |
安装扩展依赖时已包含：`pip3 install -r requirements-optional.txt`
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `action` | string | 是 | 操作类型：`get`、`set`、`list`、`delete` |
| `key` | string | 否 | 环境变量名称 |
| `value` | string | 否 | 环境变量值（仅 `set` 时需要） |
## 使用方式
直接告诉 Agent 需要配置的秘钥，Agent 会自动调用该工具：
- "帮我配置 BOCHA_API_KEY"
- "设置 OPENAI_API_KEY 为 sk-xxx"
- "查看已配置的环境变量"
配置的秘钥会自动注入到 `bash` 工具的执行环境中。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
</Frame>

50
docs/tools/index.mdx Normal file
View File

@@ -0,0 +1,50 @@
---
title: 工具概览
description: CowAgent 内置工具系统
---
工具是 Agent 访问操作系统资源的核心能力。Agent 会根据任务需求智能选择和调用工具，完成文件操作、命令执行、联网搜索、定时任务等各类操作。工具实现在项目的 `agent/tools/` 目录下。
## 内置工具
以下工具默认可用，无需额外配置：
<CardGroup cols={2}>
<Card title="read - 文件读取" icon="file" href="/tools/read">
读取文件内容，支持文本、图片、PDF
</Card>
<Card title="write - 文件写入" icon="pen" href="/tools/write">
创建或覆盖写入文件
</Card>
<Card title="edit - 文件编辑" icon="pen-to-square" href="/tools/edit">
通过精确文本替换编辑文件
</Card>
<Card title="ls - 目录列表" icon="folder-open" href="/tools/ls">
列出目录内容
</Card>
<Card title="bash - 终端" icon="terminal" href="/tools/bash">
执行系统命令
</Card>
<Card title="send - 文件发送" icon="paper-plane" href="/tools/send">
向用户发送文件或图片
</Card>
<Card title="memory - 记忆" icon="brain" href="/tools/memory">
搜索和读取长期记忆
</Card>
</CardGroup>
## 可选工具
以下工具需要安装额外依赖或配置 API Key 后启用：
<CardGroup cols={2}>
<Card title="env_config - 环境变量" icon="key" href="/tools/env-config">
管理 API Key 等秘钥配置
</Card>
<Card title="scheduler - 定时任务" icon="clock" href="/tools/scheduler">
创建和管理定时任务
</Card>
<Card title="web_search - 联网搜索" icon="magnifying-glass" href="/tools/web-search">
搜索互联网获取实时信息
</Card>
</CardGroup>

25
docs/tools/ls.mdx Normal file
View File

@@ -0,0 +1,25 @@
---
title: ls - 目录列表
description: 列出目录内容
---
# ls
列出目录内容，按字母排序，目录名带 `/` 后缀，包含隐藏文件。
## 依赖
无额外依赖，默认可用。
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `path` | string | 是 | 目录路径，相对路径基于工作空间目录 |
| `limit` | integer | 否 | 最大返回条目数，默认 500 |
## 使用场景
- 浏览项目结构
- 查找特定文件
- 检查目录是否存在

38
docs/tools/memory.mdx Normal file
View File

@@ -0,0 +1,38 @@
---
title: memory - 记忆
description: 搜索和读取长期记忆
---
# memory
记忆工具包含两个子工具：`memory_search`（搜索记忆）和 `memory_get`（读取记忆文件）。
## 依赖
无额外依赖，默认可用。由 Agent Core 的记忆系统管理。
## memory_search
搜索历史记忆，支持关键词和向量混合检索。
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `query` | string | 是 | 搜索查询 |
## memory_get
读取特定记忆文件的内容。
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `path` | string | 是 | 记忆文件的相对路径（如 `MEMORY.md`、`memory/2026-01-01.md`） |
| `start_line` | integer | 否 | 起始行号 |
| `end_line` | integer | 否 | 结束行号 |
## 工作方式
Agent 会在以下场景自动调用记忆工具：
- 用户分享重要信息时 → 存储到记忆
- 需要参考历史信息时 → 搜索相关记忆
- 对话达到一定长度时 → 提取摘要存储

26
docs/tools/read.mdx Normal file
View File

@@ -0,0 +1,26 @@
---
title: read - 文件读取
description: 读取文件内容
---
# read
读取文件内容。支持文本文件、PDF 文件、图片（返回元数据）等格式。
## 依赖
无额外依赖，默认可用。
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `path` | string | 是 | 文件路径，相对路径基于工作空间目录 |
| `offset` | integer | 否 | 起始行号（1-indexed），负值表示从末尾读取 |
| `limit` | integer | 否 | 读取行数 |
## 使用场景
- 查看配置文件、日志文件
- 读取代码文件进行分析
- 检查图片/视频的文件信息

42
docs/tools/scheduler.mdx Normal file
View File

@@ -0,0 +1,42 @@
---
title: scheduler - 定时任务
description: 创建和管理定时任务
---
# scheduler
创建和管理动态定时任务，支持灵活的调度方式和执行模式。
## 依赖
| 依赖 | 安装命令 |
| --- | --- |
| `croniter` ≥ 2.0.0 | `pip install croniter>=2.0.0` |
安装核心依赖时已包含：`pip3 install -r requirements.txt`
## 调度方式
| 方式 | 说明 |
| --- | --- |
| 一次性任务 | 在指定时间执行一次 |
| 固定间隔 | 按固定时间间隔重复执行 |
| Cron 表达式 | 使用 Cron 语法定义复杂调度规则 |
## 执行模式
- **固定消息发送**：到达触发时间时发送预设消息
- **Agent 动态任务**：到达触发时间时由 Agent 智能执行任务
## 使用方式
通过自然语言即可创建和管理定时任务：
- "每天早上 9 点给我发天气预报"
- "每隔 2 小时检查一下服务器状态"
- "明天下午 3 点提醒我开会"
- "查看所有定时任务"
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
</Frame>

25
docs/tools/send.mdx Normal file
View File

@@ -0,0 +1,25 @@
---
title: send - 文件发送
description: 向用户发送文件
---
# send
向用户发送文件（图片、视频、音频、文档等），当用户明确要求发送/分享文件时使用。
## 依赖
无额外依赖，默认可用。
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `path` | string | 是 | 文件路径，可以是绝对路径或相对于工作空间的路径 |
| `message` | string | 否 | 附带的消息说明 |
## 使用场景
- 将生成的代码或文档发送给用户
- 发送截图、图表
- 分享下载的文件

34
docs/tools/web-search.mdx Normal file
View File

@@ -0,0 +1,34 @@
---
title: web_search - 联网搜索
description: 搜索互联网获取实时信息
---
# web_search
搜索互联网获取实时信息、新闻、研究等内容。支持两个搜索后端，自动选择可用的后端。
## 依赖
需要配置至少一个搜索 API Key（通过 `env_config` 工具或工作空间 `.env` 文件配置）：
| 后端 | 环境变量 | 优先级 | 获取方式 |
| --- | --- | --- | --- |
| 博查搜索 | `BOCHA_API_KEY` | 优先使用 | [博查开放平台](https://open.bochaai.com/) |
| LinkAI 搜索 | `LINKAI_API_KEY` | 可选 | [LinkAI 控制台](https://link-ai.tech/console/interface) |
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `query` | string | 是 | 搜索关键词 |
| `count` | integer | 否 | 返回结果数量（1-50，默认 10） |
| `freshness` | string | 否 | 时间范围：`noLimit`、`oneDay`、`oneWeek`、`oneMonth`、`oneYear`，或日期范围如 `2025-01-01..2025-02-01` |
| `summary` | boolean | 否 | 是否返回页面摘要（默认 false） |
## 使用场景
当用户询问最新信息、需要事实核查或获取实时数据时，Agent 会自动调用此工具。
<Note>
如果未配置任何搜索 API Key，该工具不会被加载。
</Note>

29
docs/tools/write.mdx Normal file
View File

@@ -0,0 +1,29 @@
---
title: write - 文件写入
description: 创建或覆盖写入文件
---
# write
写入内容到文件。文件不存在则自动创建，已存在则覆盖。自动创建父目录。
## 依赖
无额外依赖，默认可用。
## 参数
| 参数 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `path` | string | 是 | 文件路径 |
| `content` | string | 是 | 要写入的内容 |
## 使用场景
- 创建新的代码文件或脚本
- 生成配置文件
- 保存处理结果
<Note>
单次写入不应超过 10KB。对于大文件，建议先创建骨架，再使用 edit 工具分块添加内容。
</Note>

101
docs/zh/configuration.mdx
View File

@@ -1,101 +0,0 @@
---
title: 配置说明
description: CowAgent 的配置文件详解
---
# 配置说明
配置文件的模板在根目录的 `config-template.json` 中，需复制该模板创建最终生效的 `config.json` 文件：
```bash
cp config-template.json config.json
```
## 核心配置项
```json
{
"channel_type": "web",
"model": "MiniMax-M2.5",
"agent": true,
"agent_workspace": "~/cow",
"agent_max_context_tokens": 40000,
"agent_max_context_turns": 30,
"agent_max_steps": 15
}
```
| 参数 | 说明 | 默认值 |
| --- | --- | --- |
| `channel_type` | 接入渠道类型 | `web` |
| `model` | 模型名称 | `MiniMax-M2.5` |
| `agent` | 是否启用 Agent 模式 | `true` |
| `agent_workspace` | Agent 工作空间路径 | `~/cow` |
| `agent_max_context_tokens` | 最大上下文 tokens | `40000` |
| `agent_max_context_turns` | 最大上下文记忆轮次 | `30` |
| `agent_max_steps` | 单次任务最大决策步数 | `15` |
## 模型 API Key 配置
根据所选模型填写对应的 API Key：
```json
{
"minimax_api_key": "",
"zhipu_ai_api_key": "",
"moonshot_api_key": "",
"ark_api_key": "",
"dashscope_api_key": "",
"claude_api_key": "",
"gemini_api_key": "",
"open_ai_api_key": ""
}
```
详细模型配置请参考 [模型说明](/zh/models)。
## 语音配置
```json
{
"speech_recognition": false,
"group_speech_recognition": false,
"voice_reply_voice": false
}
```
| 参数 | 说明 |
| --- | --- |
| `speech_recognition` | 是否开启私聊语音识别 |
| `group_speech_recognition` | 是否开启群组语音识别 |
| `voice_reply_voice` | 是否使用语音回复语音 |
## LinkAI 配置
```json
{
"use_linkai": false,
"linkai_api_key": "",
"linkai_app_code": ""
}
```
| 参数 | 说明 |
| --- | --- |
| `use_linkai` | 是否使用 LinkAI 接口 |
| `linkai_api_key` | LinkAI API Key，在 [控制台](https://link-ai.tech/console/interface) 创建 |
| `linkai_app_code` | LinkAI 应用或工作流的 code |
## 代理配置
如需使用网络代理：
```json
{
"proxy": "127.0.0.1:7890"
}
```
<Tip>
全部配置项说明可在项目 [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py) 文件中查看。
</Tip>

173
docs/zh/models.mdx
View File

@@ -1,173 +0,0 @@
---
title: 模型
description: CowAgent 支持的模型及配置方式
---
# 模型
CowAgent 支持国内外主流厂商的大语言模型，模型接口实现在项目的 `models/` 目录下。
<Note>
Agent 模式下推荐使用以下模型：MiniMax-M2.5、glm-5、kimi-k2.5、qwen3.5-plus、claude-sonnet-4-6、gemini-3.1-pro-preview，可根据效果及成本综合选择。
</Note>
## 模型配置
根据所选模型，在 `config.json` 中填写对应的模型名称和 API Key。
### MiniMax
```json
{
"model": "MiniMax-M2.5",
"minimax_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `MiniMax-M2.5`、`MiniMax-M2.1`、`MiniMax-M2.1-lightning`、`MiniMax-M2` 等 |
| `minimax_api_key` | 在 [MiniMax控制台](https://platform.minimaxi.com/user-center/basic-information/interface-key) 创建 |
### 智谱AI (GLM)
```json
{
"model": "glm-5",
"zhipu_ai_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `glm-5`、`glm-4.7`、`glm-4-plus`、`glm-4-flash` 等，参考 [模型编码](https://bigmodel.cn/dev/api/normal-model/glm-4) |
| `zhipu_ai_api_key` | 在 [智谱AI控制台](https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys) 创建 |
### 通义千问 (Qwen)
```json
{
"model": "qwen3.5-plus",
"dashscope_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `qwen3.5-plus`、`qwen3-max`、`qwen-max`、`qwen-plus` 等 |
| `dashscope_api_key` | 在 [百炼控制台](https://bailian.console.aliyun.com/?tab=model#/api-key) 创建 |
### Kimi (Moonshot)
```json
{
"model": "kimi-k2.5",
"moonshot_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `kimi-k2.5`、`kimi-k2`、`moonshot-v1-8k`、`moonshot-v1-32k` 等 |
| `moonshot_api_key` | 在 [Moonshot控制台](https://platform.moonshot.cn/console/api-keys) 创建 |
### 豆包 (Doubao)
```json
{
"model": "doubao-seed-2-0-code-preview-260215",
"ark_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 可填 `doubao-seed-2-0-code-preview-260215`、`doubao-seed-2-0-pro-260215` 等 |
| `ark_api_key` | 在 [火山方舟控制台](https://console.volcengine.com/ark/region:ark+cn-beijing/apikey) 创建 |
### Claude
```json
{
"model": "claude-sonnet-4-6",
"claude_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 支持 `claude-sonnet-4-6`、`claude-opus-4-6`、`claude-sonnet-4-5` 等，参考 [官方模型](https://docs.anthropic.com/en/docs/about-claude/models/overview) |
| `claude_api_key` | 在 [Claude控制台](https://console.anthropic.com/settings/keys) 创建 |
| `claude_api_base` | 可选，默认为 `https://api.anthropic.com/v1`，可接入第三方代理 |
### Gemini
```json
{
"model": "gemini-3.1-pro-preview",
"gemini_api_key": "YOUR_API_KEY"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 支持 `gemini-3.1-pro-preview`、`gemini-3-flash-preview`、`gemini-2.5-pro` 等，参考 [官方文档](https://ai.google.dev/gemini-api/docs/models) |
| `gemini_api_key` | 在 [Google AI Studio](https://aistudio.google.com/app/apikey) 创建 |
### OpenAI
```json
{
"model": "gpt-4.1-mini",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.openai.com/v1"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | 支持 o 系列、gpt-5.2、gpt-4.1 等，参考 [模型列表](https://platform.openai.com/docs/models) |
| `open_ai_api_key` | 在 [OpenAI平台](https://platform.openai.com/api-keys) 创建 |
| `open_ai_api_base` | 可选，修改可接入第三方代理接口 |
### DeepSeek
```json
{
"model": "deepseek-chat",
"open_ai_api_key": "YOUR_API_KEY",
"open_ai_api_base": "https://api.deepseek.com/v1",
"bot_type": "chatGPT"
}
```
| 参数 | 说明 |
| --- | --- |
| `model` | `deepseek-chat`（V3）、`deepseek-reasoner`（R1） |
| `bot_type` | 使用 OpenAI 兼容方式接入，固定为 `chatGPT` |
## OpenAI 兼容接入
除官方 SDK 接入外，多数模型也支持 OpenAI 兼容方式接入，将 `bot_type` 设为 `chatGPT`，并配置对应的 `open_ai_api_base` 和 `open_ai_api_key` 即可。
## LinkAI 平台
通过 [LinkAI](https://link-ai.tech) 平台可灵活切换多种模型，并支持知识库、工作流、插件等 Agent 能力。
```json
{
"use_linkai": true,
"linkai_api_key": "YOUR_API_KEY",
"linkai_app_code": "YOUR_APP_CODE"
}
```
| 参数 | 说明 |
| --- | --- |
| `use_linkai` | 设为 `true` 启用 LinkAI 接口 |
| `linkai_api_key` | 在 [控制台](https://link-ai.tech/console/interface) 创建 |
| `linkai_app_code` | LinkAI 智能体的 code，选填 |
<Tip>
全部模型名称可参考项目 [`common/const.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py) 文件。
</Tip>

103
docs/zh/skills.mdx
View File

@@ -1,103 +0,0 @@
---
title: 技能
description: CowAgent 的技能系统 - 为 Agent 提供无限扩展性
---
# 技能系统
技能系统为 Agent 提供无限的扩展性。每个 Skill 由说明文件、运行脚本（可选）、资源（可选）组成，描述如何完成特定类型的任务。通过 Skill 可以让 Agent 遵循说明完成复杂流程，调用各类工具或对接第三方系统。
## 技能类型
### 内置技能
位于项目的 `skills/` 目录下，根据依赖条件（API Key、系统命令等）自动判断是否启用。内置技能包括：
| 技能 | 说明 |
| --- | --- |
| `skill-creator` | 技能创造器，通过对话创建自定义技能 |
| `bocha-search` | 博查搜索，联网搜索能力 |
| `openai-image-vision` | 图像识别，使用 OpenAI 视觉模型 |
| `linkai-agent` | LinkAI 智能体，对接第三方知识库和插件 |
| `web-scraper` | 网页抓取，获取网页内容 |
### 自定义技能
由用户通过对话创建，存放在工作空间中（`~/cow/skills/`），基于自定义技能可以实现任何复杂的业务流程和第三方系统对接。
## 创建技能
通过内置的 `skill-creator` 技能，可以使用自然语言对话快速创建技能。你可以：
- 将工作流程固化为技能
- 将接口文档和示例发送给 Agent，让它直接完成对接
- 创建定制化的自动化流程
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
</Frame>
## 搜索技能
系统内置了 `bocha-search`（博查搜索）技能，配置步骤：
1. 在 [博查开放平台](https://open.bochaai.com/) 创建 API Key
2. 通过 `env_config` 工具配置 `BOCHA_SEARCH_API_KEY`，或直接发送给 Agent
## 图像识别
内置 `openai-image-vision` 技能，支持使用 `gpt-4.1-mini`、`gpt-4.1` 等图像识别模型。
配置 `OPENAI_API_KEY` 后即可使用，可通过 `config.json` 或 `env_config` 工具进行维护。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
</Frame>
## LinkAI 智能体
`linkai-agent` 技能可以将 [LinkAI](https://link-ai.tech/) 上的所有智能体作为 Skill 交给 Agent 使用，实现多智能体决策。
### 配置方式
1. 配置 `LINKAI_API_KEY`（通过 `env_config` 工具或 `config.json` 中的 `linkai_api_key`）
2. 在 `skills/linkai-agent/config.json` 中添加智能体说明：
```json
{
"apps": [
{
"app_code": "G7z6vKwp",
"app_name": "LinkAI客服助手",
"app_description": "当用户需要了解LinkAI平台相关问题时才选择该助手"
},
{
"app_code": "SFY5x7JR",
"app_name": "内容创作助手",
"app_description": "当用户需要创作图片或视频时才使用该助手"
}
]
}
```
Agent 会根据智能体的名称和描述进行决策，通过 `app_code` 调用对应的应用或工作流。
<Frame>
<img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
</Frame>
## 技能文件结构
每个技能目录的结构如下：
```
skills/
├── my-skill/
│ ├── SKILL.md # Skill description and instructions
│ ├── run.py # Execution script (optional)
│ └── resources/ # Additional resources (optional)
```
<Tip>
自定义技能的开发文档可参考 [Skill创造器说明](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md)。
</Tip>