Ubuntu22.04 安装与配置 OpenClaw AI 助手教程

一键安装

curl -fsSL https://clawd.org.cn/install.sh | sudo bash

输入 Y 确认安装。

需要配置 DeepSeek API Key。访问 https://platform.deepseek.com/sign_in 注册并获取 API Key，在安装终端中输入。

设置通道 配置飞书

需创建飞书机器人。访问 https://open.feishu.cn 进入开发者后台，注册用户并创建 AI 机器人。

创建成功后记录 App ID 和 App Secret。在后续安装终端中填入 App ID 和 Secret。

也可使用命令单独配置：

openclaw-cn configure --section channels

如有问题，运行 openclaw-cn onboard --install-daemon 重新配置。

若 Gateway 未安装导致无法打开网页端，执行以下命令安装必备工具：

sudo apt install net-tools

让 ai 员工更好用

加入免费的模型

配置 GLM-4.7-Flash 官方免费 API。访问 https://bigmodel.cn/ 注册开发者并获取 API Key。

在控制台新建 API Key 后复制，写入 openclaw.json 文件：

{
  "models": {
    "providers": {
      "glm": {
        "baseUrl": "https://open.bigmodel.cn/api/paas/v4",
        "apiKey": "你的 apiKey",
        "api": "openai-completions",
        "models": [
          {
            "id": "glm-4.7-flash",
            "name": "GLM-4.7 Flash",
            "contextWindow": 128000,
            "maxTokens": 4096,
            "reasoning": false,
            "input": ["text"],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            }
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "glm/glm-4.7-flash"
      },
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  }
}

重启 OpenClaw：

openclaw-cn gateway restart

配置钉钉

访问 https://open-dev.dingtalk.com 在钉钉开发者平台获取 Client ID (AppKey) 和 Client Secret (AppSecret)。

在'权限管理'中添加权限：

• Card.Instance.Write（卡片实例写权限）
• Card.Streaming.Write（卡片流式写权限）
• im:message（消息相关权限）

安装钉钉插件（默认未内置）：

openclaw-cn plugins install https://github.com/soimy/clawdbot-channel-dingtalk.git

在 GLM-4.7-Flash 基础上加入 deepseek

修改 openclaw.json 配置文件加入 DeepSeek API Key，当 GLM 免费 Token 不足时自动切换。 重启服务：

openclaw-cn gateway restart

加入 minimax 和豆包模型

1. MiniMax M2.5：访问 https://api.minimax.chat/ 注册登录获取 API Key。
2. Seedance2.0：访问 https://console.volcengine.com/ark/ 开通火山方舟服务，在'API Key 管理'页面创建 Key。

之后配置 openclaw.json 即可接入多个大模型。

配置 web 搜索

访问 https://exa.ai/ 免费注册并获取 API Key。

将 API Key 告知 OpenClaw 进行配置：

export EXA_API_KEY="YOUR_API_KEY"

或在 .env 文件中添加：

EXA_API_KEY=YOUR_API_KEY

重启服务：

openclaw-cn gateway restart

.env File

EXA_API_KEY=YOUR_API_KEY

Exa MCP Server for OpenAI Codex

为 OpenAI Codex 提供实时 Web 搜索、代码上下文和公司研究功能。

运行命令：

codex mcp add exa --url https://mcp.exa.ai/mcp?exaApiKey=YOUR_API_KEY

启用特定工具：

https://mcp.exa.ai/mcp?exaApiKey=YOUR_API_KEY&tools=web_search_exa,get_code_context_exa,people_search_exa

启用所有工具：

https://mcp.exa.ai/mcp?exaApiKey=YOUR_API_KEY&tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check

故障排除： 如果工具未显示，更新配置后重启 MCP 客户端。

Quick Start

cURL

curl -X POST 'https://api.exa.ai/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "query": "latest developments in AI safety research", "type": "auto", "num_results": 10, "contents": { "text": { "max_characters": 20000 } } }'

Function Calling / Tool Use

函数调用允许 AI 代理根据对话上下文动态决定何时搜索网络。

OpenAI Function Calling

import json
from openai import OpenAI
from exa_py import Exa

openai = OpenAI()
exa = Exa()

tools = [{"type":"function","function":{"name":"exa_search","description":"Search the web for current information.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"Search query"}},"required":["query"]}}}]

def exa_search(query:str)->str:
    results = exa.search_and_contents(query,type="auto", num_results=10, text={"max_characters":20000})
    return "\n".join([f"{r.title}: {r.url}" for r in results.results])

messages = [{"role":"user","content":"What's the latest in AI safety?"}]
response = openai.chat.completions.create(model="gpt-4o", messages=messages, tools=tools)
if response.choices[0].message.tool_calls:
    tool_call = response.choices[0].message.tool_calls[0]
    search_results = exa_search(json.loads(tool_call.function.arguments)["query"])
    messages.append(response.choices[0].message)
    messages.append({"role":"tool","tool_call_id": tool_call.id,"content": search_results})
final = openai.chat.completions.create(model="gpt-4o", messages=messages)
print(final.choices[0].message.content)

Anthropic Tool Use

import anthropic
from exa_py import Exa

client = anthropic.Anthropic()
exa = Exa()

tools = [{"name":"exa_search","description":"Search the web for current information.","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query"}},"required":["query"]}}]

def exa_search(query:str)->str:
    results = exa.search_and_contents(query,type="auto", num_results=10, text={"max_characters":20000})
    return "\n".join([f"{r.title}: {r.url}" for r in results.results])

messages = [{"role":"user","content":"Latest quantum computing developments?"}]
response = client.messages.create(model="claude-sonnet-4-20250514", max_tokens=4096, tools=tools, messages=messages)
if response.stop_reason == "tool_use":
    tool_use = next(b for b in response.content if b.type=="tool_use")
    tool_result = exa_search(tool_use.input["query"])
    messages.append({"role":"assistant","content": response.content})
    messages.append({"role":"user","content":[{"type":"tool_result","tool_use_id": tool_use.id,"content": tool_result}]})
final = client.messages.create(model="claude-sonnet-4-20250514", max_tokens=4096, tools=tools, messages=messages)
print(final.content[0].text)

Search Type Reference

Tip: type="auto" works well for most queries. Use type="deep" when you need thorough research results.

Content Configuration

Choose ONE content type per request:

Warning: Using text: true can significantly increase token count. Add max_characters limit or use highlights.

Domain Filtering (Optional)

Usually not needed. Example:

{"includeDomains":["arxiv.org","github.com"],"excludeDomains":["pinterest.com"]}

Web Search Tool

{"query":"latest developments in AI safety research","num_results":10,"contents":{"text":{"max_characters":20000}}}

Tips:

• Use type: "auto" for most queries
• Great for building search-powered chatbots or agents
• Combine with contents for RAG workflows

Category Examples

Use category filters to search dedicated indexes.

People Search (category: "people")

Find people by role, expertise, or what they work on.

curl -X POST 'https://api.exa.ai/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "query": "software engineer distributed systems", "category": "people", "type": "auto", "num_results": 10 }'

Tips: Use SINGULAR form. Describe what they work on.

Company Search (category: "company")

Find companies by industry, criteria, or attributes.

curl -X POST 'https://api.exa.ai/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "query": "AI startup healthcare", "category": "company", "type": "auto", "num_results": 10 }'

Tips: Use SINGULAR form. Simple entity queries.

News Search (category: "news")

News articles.

curl -X POST 'https://api.exa.ai/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "query": "OpenAI announcements", "category": "news", "type": "auto", "num_results": 10, "contents": { "text": { "max_characters": 20000 } } }'

Tips: Use livecrawl: "preferred" for breaking news.

Research Papers (category: "research paper")

Academic papers.

curl -X POST 'https://api.exa.ai/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "query": "transformer architecture improvements", "category": "research paper", "type": "auto", "num_results": 10, "contents": { "text": { "max_characters": 20000 } } }'

Tips: Includes arxiv.org, paperswithcode.com.

Tweet Search (category: "tweet")

Twitter/X posts.

curl -X POST 'https://api.exa.ai/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "query": "AI safety discussion", "category": "tweet", "type": "auto", "num_results": 10, "contents": { "text": { "max_characters": 20000 } } }'

Tips: Good for real-time discussions.

Content Freshness (maxAgeHours)

maxAgeHours sets the maximum acceptable age for cached content.

Other Endpoints

Beyond /search, Exa offers these endpoints:

Example - Get contents for URLs:

POST /contents
{"urls":["https://example.com/article"],"text":{"max_characters":20000}}

Troubleshooting

Results not relevant?

1. Try type: "auto"
2. Try type: "deep"
3. Refine query
4. Check category matches your use case

Need structured data from search?

1. Use type: "deep" or type: "deep-reasoning" with outputSchema

Results too slow?

1. Use type: "fast"
2. Reduce num_results
3. Skip contents if you only need URLs

No results?

1. Remove filters
2. Simplify query
3. Try type: "auto"

Resources

• Docs: https://exa.ai/docs
• Dashboard: https://dashboard.exa.ai
• API Status: https://status.exa.ai