copaw-ai-assistant

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

CoPaw AI Assistant Skill

CoPaw AI助手技能

Skill by ara.so — Daily 2026 Skills collection.

CoPaw is a personal AI assistant framework you deploy on your own machine or in the cloud. It connects to multiple chat platforms (DingTalk, Feishu, QQ, Discord, iMessage, Telegram, Mattermost, Matrix, MQTT) through a single agent, supports custom Python skills, scheduled cron jobs, local and cloud LLMs, and provides a web Console at

http://127.0.0.1:8088/

由ara.so开发的技能——属于Daily 2026技能合集。

CoPaw是一款可部署在本地机器或云端的个人AI助手框架。它通过单个Agent连接多个聊天平台（钉钉、飞书、QQ、Discord、iMessage、Telegram、Mattermost、Matrix、MQTT），支持自定义Python技能、定时cron任务、本地及云端LLM，并提供Web控制台，访问地址为

http://127.0.0.1:8088/

。

Installation

安装

pip (recommended if Python 3.10–3.13 is available)

pip安装（若Python版本为3.10–3.13，推荐使用此方式）

bash

pip install copaw
copaw init --defaults    # non-interactive setup with sensible defaults
copaw app                # starts the web Console + backend

bash

pip install copaw
copaw init --defaults    # 使用合理默认值的非交互式初始化
copaw app                # 启动Web控制台 + 后端服务

Script install (no Python setup required)

脚本安装（无需预先配置Python）

macOS / Linux:

bash

curl -fsSL https://copaw.agentscope.io/install.sh | bash

macOS / Linux：

bash

curl -fsSL https://copaw.agentscope.io/install.sh | bash

With Ollama support:

带Ollama支持：

curl -fsSL https://copaw.agentscope.io/install.sh | bash -s -- --extras ollama

Multiple extras:

多扩展支持：

curl -fsSL https://copaw.agentscope.io/install.sh | bash -s -- --extras ollama,llamacpp


**Windows CMD:**
```cmd
curl -fsSL https://copaw.agentscope.io/install.bat -o install.bat && install.bat

Windows PowerShell:

powershell

irm https://copaw.agentscope.io/install.ps1 | iex

After script install, open a new terminal:

bash

copaw init --defaults
copaw app

curl -fsSL https://copaw.agentscope.io/install.sh | bash -s -- --extras ollama,llamacpp


**Windows CMD：**
```cmd
curl -fsSL https://copaw.agentscope.io/install.bat -o install.bat && install.bat

Windows PowerShell：

powershell

irm https://copaw.agentscope.io/install.ps1 | iex

脚本安装完成后，打开新终端执行：

bash

copaw init --defaults
copaw app

Install from source

从源码安装

bash

git clone https://github.com/agentscope-ai/CoPaw.git
cd CoPaw
pip install -e ".[dev]"
copaw init --defaults
copaw app

bash

git clone https://github.com/agentscope-ai/CoPaw.git
cd CoPaw
pip install -e ".[dev]"
copaw init --defaults
copaw app

CLI Reference

CLI参考

bash

copaw init                  # interactive workspace setup
copaw init --defaults       # non-interactive setup
copaw app                   # start the Console (http://127.0.0.1:8088/)
copaw app --port 8090       # use a custom port
copaw --help                # list all commands

bash

copaw init                  # 交互式工作区初始化
copaw init --defaults       # 非交互式初始化
copaw app                   # 启动控制台（地址：http://127.0.0.1:8088/）
copaw app --port 8090       # 使用自定义端口
copaw --help                # 查看所有命令

Workspace Structure

工作区结构

After

copaw init

, a workspace is created (default:

~/.copaw/workspace/

~/.copaw/workspace/
├── config.yaml          # agent, provider, channel configuration
├── skills/              # custom skill files (auto-loaded)
│   └── my_skill.py
├── memory/              # conversation memory storage
└── logs/                # runtime logs

执行

copaw init

后会创建工作区（默认路径：

~/.copaw/workspace/

）：

~/.copaw/workspace/
├── config.yaml          # Agent、提供商、渠道配置文件
├── skills/              # 自定义技能文件（自动加载）
│   └── my_skill.py
├── memory/              # 对话记忆存储目录
└── logs/                # 运行时日志目录

Configuration (

config.yaml

)

配置文件（

config.yaml

）

copaw init

generates this file. Edit it directly or use the Console UI.

copaw init

会生成此文件，可直接编辑或通过控制台UI修改。

LLM Provider (OpenAI-compatible)

LLM提供商（兼容OpenAI）

yaml

providers:
  - id: openai-main
    type: openai
    api_key: ${OPENAI_API_KEY}        # use env var reference
    model: gpt-4o
    base_url: https://api.openai.com/v1

  - id: local-ollama
    type: ollama
    model: llama3.2
    base_url: http://localhost:11434

yaml

providers:
  - id: openai-main
    type: openai
    api_key: ${OPENAI_API_KEY}        # 使用环境变量引用
    model: gpt-4o
    base_url: https://api.openai.com/v1

  - id: local-ollama
    type: ollama
    model: llama3.2
    base_url: http://localhost:11434

Agent Settings

Agent设置

yaml

agent:
  name: CoPaw
  language: en                        # en, zh, ja, etc.
  provider_id: openai-main
  context_limit: 8000

yaml

agent:
  name: CoPaw
  language: en                        # 支持en、zh、ja等
  provider_id: openai-main
  context_limit: 8000

Channel: DingTalk

渠道：钉钉

yaml

channels:
  - type: dingtalk
    app_key: ${DINGTALK_APP_KEY}
    app_secret: ${DINGTALK_APP_SECRET}
    agent_id: ${DINGTALK_AGENT_ID}
    mention_only: true                # only respond when @mentioned in groups

yaml

channels:
  - type: dingtalk
    app_key: ${DINGTALK_APP_KEY}
    app_secret: ${DINGTALK_APP_SECRET}
    agent_id: ${DINGTALK_AGENT_ID}
    mention_only: true                # 仅在群聊中被@时响应

Channel: Feishu (Lark)

渠道：飞书（Lark）

yaml

channels:
  - type: feishu
    app_id: ${FEISHU_APP_ID}
    app_secret: ${FEISHU_APP_SECRET}
    mention_only: false

yaml

channels:
  - type: feishu
    app_id: ${FEISHU_APP_ID}
    app_secret: ${FEISHU_APP_SECRET}
    mention_only: false

Channel: Discord

渠道：Discord

yaml

channels:
  - type: discord
    token: ${DISCORD_BOT_TOKEN}
    mention_only: true

yaml

channels:
  - type: discord
    token: ${DISCORD_BOT_TOKEN}
    mention_only: true

Channel: Telegram

渠道：Telegram

yaml

channels:
  - type: telegram
    token: ${TELEGRAM_BOT_TOKEN}

yaml

channels:
  - type: telegram
    token: ${TELEGRAM_BOT_TOKEN}

Channel: QQ

渠道：QQ

yaml

channels:
  - type: qq
    uin: ${QQ_UIN}
    password: ${QQ_PASSWORD}

yaml

channels:
  - type: qq
    uin: ${QQ_UIN}
    password: ${QQ_PASSWORD}

Channel: Mattermost

渠道：Mattermost

yaml

channels:
  - type: mattermost
    url: ${MATTERMOST_URL}
    token: ${MATTERMOST_TOKEN}
    team: my-team

yaml

channels:
  - type: mattermost
    url: ${MATTERMOST_URL}
    token: ${MATTERMOST_TOKEN}
    team: my-team

Channel: Matrix

渠道：Matrix

yaml

channels:
  - type: matrix
    homeserver: ${MATRIX_HOMESERVER}
    user_id: ${MATRIX_USER_ID}
    access_token: ${MATRIX_ACCESS_TOKEN}

yaml

channels:
  - type: matrix
    homeserver: ${MATRIX_HOMESERVER}
    user_id: ${MATRIX_USER_ID}
    access_token: ${MATRIX_ACCESS_TOKEN}

Custom Skills

自定义技能

Skills are Python files placed in

~/.copaw/workspace/skills/

. They are auto-loaded when CoPaw starts — no registration step needed.

技能为放置在

~/.copaw/workspace/skills/

目录下的Python文件，CoPaw启动时会自动加载，无需额外注册步骤。

Minimal skill structure

最简技能结构

python

undefined

python

undefined

~/.copaw/workspace/skills/weather.py

SKILL_NAME = "get_weather" SKILL_DESCRIPTION = "Get current weather for a city"

Tool schema (OpenAI function-calling format)

工具Schema（OpenAI函数调用格式）

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": { "type": "object", "properties": { "city": { "type": "string", "description": "City name, e.g. 'Tokyo'" } }, "required": ["city"] } } }

def get_weather(city: str) -> str: """Fetch weather data for the given city.""" import os import requests

api_key = os.environ["OPENWEATHER_API_KEY"]
url = f"https://api.openweathermap.org/data/2.5/weather"
resp = requests.get(url, params={"q": city, "appid": api_key, "units": "metric"})
resp.raise_for_status()
data = resp.json()
temp = data["main"]["temp"]
desc = data["weather"][0]["description"]
return f"{city}: {temp}°C, {desc}"

undefined

def get_weather(city: str) -> str: """获取指定城市的当前天气。""" import os import requests

api_key = os.environ["OPENWEATHER_API_KEY"]
url = f"https://api.openweathermap.org/data/2.5/weather"
resp = requests.get(url, params={"q": city, "appid": api_key, "units": "metric"})
resp.raise_for_status()
data = resp.json()
temp = data["main"]["temp"]
desc = data["weather"][0]["description"]
return f"{city}: {temp}°C, {desc}"

undefined

Skill with async support

支持异步的技能

python

undefined

python

undefined

~/.copaw/workspace/skills/summarize_url.py

SKILL_NAME = "summarize_url" SKILL_DESCRIPTION = "Fetch and summarize the content of a URL"

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": { "type": "object", "properties": { "url": {"type": "string", "description": "The URL to summarize"} }, "required": ["url"] } } }

async def summarize_url(url: str) -> str: import httpx

async with httpx.AsyncClient(timeout=15) as client:
    resp = await client.get(url)
    text = resp.text[:4000]   # truncate for context limit
return f"Content preview from {url}:\n{text}"

undefined

SKILL_NAME = "summarize_url" SKILL_DESCRIPTION = "Fetch and summarize the content of a URL"

async def summarize_url(url: str) -> str: import httpx

async with httpx.AsyncClient(timeout=15) as client:
    resp = await client.get(url)
    text = resp.text[:4000]   # 截断内容以符合上下文限制
return f"Content preview from {url}:\n{text}"

undefined

Skill returning structured data

返回结构化数据的技能

python

undefined

python

undefined

~/.copaw/workspace/skills/list_files.py

import os import json

SKILL_NAME = "list_files" SKILL_DESCRIPTION = "List files in a directory"

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": { "type": "object", "properties": { "path": { "type": "string", "description": "Absolute or relative directory path" }, "extension": { "type": "string", "description": "Filter by extension, e.g. '.py'. Optional." } }, "required": ["path"] } } }

def list_files(path: str, extension: str = "") -> str: entries = os.listdir(os.path.expanduser(path)) if extension: entries = [e for e in entries if e.endswith(extension)] return json.dumps(sorted(entries))

---

import os import json

SKILL_NAME = "list_files" SKILL_DESCRIPTION = "List files in a directory"

---

Cron / Scheduled Tasks

Cron/定时任务

Define cron jobs in

config.yaml

to run skills on a schedule and push results to a channel:

yaml

cron:
  - id: daily-digest
    schedule: "0 8 * * *"            # every day at 08:00
    skill: get_weather
    skill_args:
      city: "Tokyo"
    channel_id: dingtalk-main         # matches a channel id below
    message_template: "Good morning! Today's weather: {result}"

  - id: hourly-news
    schedule: "0 * * * *"
    skill: fetch_tech_news
    channel_id: discord-main

在

config.yaml

中定义定时任务，可按计划运行技能并将结果推送到指定渠道：

yaml

cron:
  - id: daily-digest
    schedule: "0 8 * * *"            # 每天08:00执行
    skill: get_weather
    skill_args:
      city: "Tokyo"
    channel_id: dingtalk-main         # 与下方渠道ID匹配
    message_template: "Good morning! Today's weather: {result}"

  - id: hourly-news
    schedule: "0 * * * *"
    skill: fetch_tech_news
    channel_id: discord-main

Local Model Setup

本地模型配置

Ollama

bash

undefined

bash

undefined

Install Ollama: https://ollama.ai

安装Ollama：https://ollama.ai

ollama pull llama3.2 ollama serve # starts on http://localhost:11434


```yaml

ollama pull llama3.2 ollama serve # 启动服务，默认地址http://localhost:11434


```yaml

config.yaml

providers:

id: ollama-local type: ollama model: llama3.2 base_url: http://localhost:11434

undefined

providers:

id: ollama-local type: ollama model: llama3.2 base_url: http://localhost:11434

undefined

LM Studio

yaml

providers:
  - id: lmstudio-local
    type: lmstudio
    model: lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF
    base_url: http://localhost:1234/v1

yaml

providers:
  - id: lmstudio-local
    type: lmstudio
    model: lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF
    base_url: http://localhost:1234/v1

llama.cpp (extra required)

llama.cpp（需安装扩展）

bash

pip install "copaw[llamacpp]"

yaml

providers:
  - id: llamacpp-local
    type: llamacpp
    model_path: /path/to/model.gguf

bash

pip install "copaw[llamacpp]"

yaml

providers:
  - id: llamacpp-local
    type: llamacpp
    model_path: /path/to/model.gguf

Tool Guard (Security)

工具防护（安全功能）

Tool Guard blocks risky tool calls and requires user approval before execution. Configure in

config.yaml

yaml

agent:
  tool_guard:
    enabled: true
    risk_patterns:
      - "rm -rf"
      - "DROP TABLE"
      - "os.system"
    auto_approve_low_risk: true

When a call is blocked, the Console shows an approval prompt. The user can approve or deny before the tool runs.

工具防护可拦截高风险工具调用，执行前需用户确认。在

config.yaml

中配置：

yaml

agent:
  tool_guard:
    enabled: true
    risk_patterns:
      - "rm -rf"
      - "DROP TABLE"
      - "os.system"
    auto_approve_low_risk: true

当调用被拦截时，控制台会显示确认提示，用户可选择批准或拒绝后再执行工具。

Token Usage Tracking

令牌使用追踪

Token usage is tracked automatically and visible in the Console dashboard. Access programmatically:

python

undefined

系统会自动追踪令牌使用情况，可在控制台仪表板查看，也可通过代码调用获取：

python

undefined

In a skill or debug script

在技能或调试脚本中使用

from copaw.telemetry import get_usage_summary

summary = get_usage_summary() print(summary)

from copaw.telemetry import get_usage_summary

summary = get_usage_summary() print(summary)

{'total_tokens': 142300, 'prompt_tokens': 98200, 'completion_tokens': 44100, 'by_provider': {...}}

---

---

Environment Variables

环境变量

Set these before running

copaw app

, or reference them in

config.yaml

${VAR_NAME}

bash

undefined

在运行

copaw app

前设置，或在

config.yaml

中通过

${VAR_NAME}

引用：

bash

undefined

LLM providers

LLM提供商

export OPENAI_API_KEY=... export ANTHROPIC_API_KEY=...

Channels

聊天渠道

export DINGTALK_APP_KEY=... export DINGTALK_APP_SECRET=... export DINGTALK_AGENT_ID=...

export FEISHU_APP_ID=... export FEISHU_APP_SECRET=...

export DISCORD_BOT_TOKEN=... export TELEGRAM_BOT_TOKEN=...

export QQ_UIN=... export QQ_PASSWORD=...

export MATTERMOST_URL=... export MATTERMOST_TOKEN=...

export MATRIX_HOMESERVER=... export MATRIX_USER_ID=... export MATRIX_ACCESS_TOKEN=...

export DINGTALK_APP_KEY=... export DINGTALK_APP_SECRET=... export DINGTALK_AGENT_ID=...

export FEISHU_APP_ID=... export FEISHU_APP_SECRET=...

export DISCORD_BOT_TOKEN=... export TELEGRAM_BOT_TOKEN=...

export QQ_UIN=... export QQ_PASSWORD=...

export MATTERMOST_URL=... export MATTERMOST_TOKEN=...

export MATRIX_HOMESERVER=... export MATRIX_USER_ID=... export MATRIX_ACCESS_TOKEN=...

Custom skill secrets

自定义技能密钥

export OPENWEATHER_API_KEY=...

---

export OPENWEATHER_API_KEY=...

---

Common Patterns

常见使用场景

Pattern: Morning briefing to DingTalk

场景：钉钉早报推送

yaml

undefined

yaml

undefined

config.yaml excerpt

config.yaml 节选

channels:

id: dingtalk-main type: dingtalk app_key: ${DINGTALK_APP_KEY} app_secret: ${DINGTALK_APP_SECRET} agent_id: ${DINGTALK_AGENT_ID}

cron:

id: morning-brief schedule: "30 7 * * 1-5" # weekdays 07:30 skill: daily_briefing channel_id: dingtalk-main


```python

channels:

id: dingtalk-main type: dingtalk app_key: ${DINGTALK_APP_KEY} app_secret: ${DINGTALK_APP_SECRET} agent_id: ${DINGTALK_AGENT_ID}

cron:

id: morning-brief schedule: "30 7 * * 1-5" # 工作日07:30执行 skill: daily_briefing channel_id: dingtalk-main


```python

skills/daily_briefing.py

SKILL_NAME = "daily_briefing" SKILL_DESCRIPTION = "Compile a morning briefing with weather and news"

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": {"type": "object", "properties": {}, "required": []} } }

def daily_briefing() -> str: import os, requests, datetime

today = datetime.date.today().strftime("%A, %B %d")
# Add your own data sources here
return f"Good morning! Today is {today}. Have a productive day!"

undefined

SKILL_NAME = "daily_briefing" SKILL_DESCRIPTION = "Compile a morning briefing with weather and news"

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": {"type": "object", "properties": {}, "required": []} } }

def daily_briefing() -> str: import os, requests, datetime

today = datetime.date.today().strftime("%A, %B %d")
# 在此添加自定义数据源
return f"Good morning! Today is {today}. Have a productive day!"

undefined

Pattern: Multi-channel broadcast

场景：多渠道消息广播

python

undefined

python

undefined

skills/broadcast.py

SKILL_NAME = "broadcast_message" SKILL_DESCRIPTION = "Send a message to all configured channels"

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": { "type": "object", "properties": { "message": {"type": "string", "description": "Message to broadcast"} }, "required": ["message"] } } }

def broadcast_message(message: str) -> str: # CoPaw handles routing; return the message and let the agent deliver it return f"[BROADCAST] {message}"

undefined

SKILL_NAME = "broadcast_message" SKILL_DESCRIPTION = "Send a message to all configured channels"

def broadcast_message(message: str) -> str: # CoPaw会处理路由逻辑；返回消息后由Agent完成分发 return f"[BROADCAST] {message}"

undefined

Pattern: File summarization skill

场景：文件摘要技能

python

undefined

python

undefined

skills/summarize_file.py

SKILL_NAME = "summarize_file" SKILL_DESCRIPTION = "Read and summarize a local file"

SKILL_SCHEMA = { "type": "function", "function": { "name": SKILL_NAME, "description": SKILL_DESCRIPTION, "parameters": { "type": "object", "properties": { "file_path": {"type": "string", "description": "Absolute path to the file"} }, "required": ["file_path"] } } }

def summarize_file(file_path: str) -> str: import os

path = os.path.expanduser(file_path)
if not os.path.exists(path):
    return f"File not found: {path}"

with open(path, "r", encoding="utf-8", errors="ignore") as f:
    content = f.read(8000)

return f"File: {path}\nSize: {os.path.getsize(path)} bytes\nContent preview:\n{content}"

---

SKILL_NAME = "summarize_file" SKILL_DESCRIPTION = "Read and summarize a local file"

def summarize_file(file_path: str) -> str: import os

path = os.path.expanduser(file_path)
if not os.path.exists(path):
    return f"File not found: {path}"

with open(path, "r", encoding="utf-8", errors="ignore") as f:
    content = f.read(8000)

return f"File: {path}\nSize: {os.path.getsize(path)} bytes\nContent preview:\n{content}"

---

Troubleshooting

故障排查

Console not accessible at port 8088

控制台无法在8088端口访问

bash

undefined

bash

undefined

Use a different port

使用其他端口

copaw app --port 8090

Check if another process is using 8088

检查8088端口是否被占用

lsof -i :8088 # macOS/Linux netstat -ano | findstr :8088 # Windows

undefined

lsof -i :8088 # macOS/Linux netstat -ano | findstr :8088 # Windows

undefined

Skills not loading

技能未加载

Confirm the skill file is in
```
~/.copaw/workspace/skills/
```
Confirm
```
SKILL_NAME
```
,
```
SKILL_DESCRIPTION
```
,
```
SKILL_SCHEMA
```
, and the handler function are all defined at module level
Check
```
~/.copaw/workspace/logs/
```
for import errors
Restart
```
copaw app
```
after adding new skill files

确认技能文件放置在
```
~/.copaw/workspace/skills/
```
目录下
确认
```
SKILL_NAME
```
、
```
SKILL_DESCRIPTION
```
、
```
SKILL_SCHEMA
```
以及处理函数均定义在模块顶层
查看
```
~/.copaw/workspace/logs/
```
目录下的导入错误日志
添加新技能文件后需重启
```
copaw app
```

Channel not receiving messages

渠道未接收消息

Verify credentials are set correctly (env vars or
```
config.yaml
```
)
Check the Console → Channels page for connection status
For DingTalk/Feishu/Discord with
```
mention_only: true
```
, the bot must be @mentioned
Discord messages over 2000 characters are split automatically — ensure the bot has
```
Send Messages
```
permission

验证凭证设置正确（环境变量或
```
config.yaml
```
）
查看控制台→渠道页面的连接状态
对于设置
```
mention_only: true
```
的钉钉/飞书/Discord，需@机器人才能触发响应
Discord消息超过2000字符会自动拆分——确保机器人拥有
```
Send Messages
```
权限

LLM provider connection fails

LLM提供商连接失败

bash

undefined

bash

undefined

Test provider from CLI (Console → Providers → Test Connection)

通过CLI测试提供商连接（控制台→提供商→测试连接）

Or check logs:

或查看日志：

tail -f ~/.copaw/workspace/logs/copaw.log


- For Ollama: confirm `ollama serve` is running and `base_url` matches
- For OpenAI-compatible APIs: verify `base_url` ends with `/v1`
- LLM calls auto-retry with exponential backoff — transient failures resolve automatically

tail -f ~/.copaw/workspace/logs/copaw.log


- 对于Ollama：确认`ollama serve`已启动且`base_url`匹配
- 对于兼容OpenAI的API：验证`base_url`以`/v1`结尾
- LLM调用会自动指数退避重试——临时故障会自动恢复

Windows encoding issues

Windows编码问题

cmd

undefined

cmd

undefined

Set UTF-8 encoding for CMD

为CMD设置UTF-8编码

chcp 65001


Or set in environment:
```bash
export PYTHONIOENCODING=utf-8

chcp 65001


或在环境变量中设置：
```bash
export PYTHONIOENCODING=utf-8

Workspace reset

工作区重置

bash

undefined

bash

undefined

Reinitialize workspace (preserves skills/)

重新初始化工作区（保留skills/目录）

copaw init

Full reset (destructive)

完全重置（会删除所有数据）

rm -rf ~/.copaw/workspace copaw init --defaults

---

rm -rf ~/.copaw/workspace copaw init --defaults

---

ModelScope Cloud Deployment

ModelScope云端部署

For one-click cloud deployment without local setup:

Visit ModelScope CoPaw Studio
Fork the studio to your account
Set environment variables in the studio settings
Start the studio — Console is accessible via the studio URL

无需本地配置，一键云端部署：

访问ModelScope CoPaw Studio
将Studio复刻到自己的账号
在Studio设置中配置环境变量
启动Studio——控制台可通过Studio地址访问

Key Links

关键链接

Documentation: https://copaw.agentscope.io/
Channel setup guides: https://copaw.agentscope.io/docs/channels
Release notes: https://agentscope-ai.github.io/CoPaw/release-notes
GitHub: https://github.com/agentscope-ai/CoPaw
PyPI: https://pypi.org/project/copaw/
Discord community: https://discord.gg/eYMpfnkG8h

官方文档: https://copaw.agentscope.io/
渠道配置指南: https://copaw.agentscope.io/docs/channels
版本更新日志: https://agentscope-ai.github.io/CoPaw/release-notes
GitHub仓库: https://github.com/agentscope-ai/CoPaw
PyPI地址: https://pypi.org/project/copaw/
Discord社区: https://discord.gg/eYMpfnkG8h

copaw-ai-assistant

Original

Translation

CoPaw AI Assistant Skill

CoPaw AI助手技能

Installation

安装

pip (recommended if Python 3.10–3.13 is available)

pip安装（若Python版本为3.10–3.13，推荐使用此方式）

Script install (no Python setup required)

脚本安装（无需预先配置Python）

With Ollama support:

带Ollama支持：

Multiple extras:

多扩展支持：

Install from source

从源码安装

CLI Reference

CLI参考

Workspace Structure

工作区结构

Configuration (config.yaml)

配置文件（config.yaml）

LLM Provider (OpenAI-compatible)

LLM提供商（兼容OpenAI）

Agent Settings

Agent设置

Channel: DingTalk

渠道：钉钉

Channel: Feishu (Lark)

渠道：飞书（Lark）

Channel: Discord

渠道：Discord

Channel: Telegram

渠道：Telegram

Channel: QQ

渠道：QQ

Channel: Mattermost

渠道：Mattermost

Channel: Matrix

渠道：Matrix

Custom Skills

自定义技能

Minimal skill structure

最简技能结构

~/.copaw/workspace/skills/weather.py

~/.copaw/workspace/skills/weather.py

Tool schema (OpenAI function-calling format)

工具Schema（OpenAI函数调用格式）

Skill with async support

支持异步的技能

~/.copaw/workspace/skills/summarize_url.py

~/.copaw/workspace/skills/summarize_url.py

Skill returning structured data

返回结构化数据的技能

~/.copaw/workspace/skills/list_files.py

~/.copaw/workspace/skills/list_files.py

Cron / Scheduled Tasks

Cron/定时任务

Local Model Setup

本地模型配置

Ollama

Ollama

Install Ollama: https://ollama.ai

安装Ollama：https://ollama.ai

config.yaml

config.yaml

LM Studio

LM Studio

llama.cpp (extra required)

llama.cpp（需安装扩展）

Tool Guard (Security)

工具防护（安全功能）

Token Usage Tracking

令牌使用追踪

In a skill or debug script

在技能或调试脚本中使用

{'total_tokens': 142300, 'prompt_tokens': 98200, 'completion_tokens': 44100, 'by_provider': {...}}

{'total_tokens': 142300, 'prompt_tokens': 98200, 'completion_tokens': 44100, 'by_provider': {...}}

Environment Variables

Configuration (
`config.yaml`
)

配置文件（
`config.yaml`
）