Raspberry Pi Compute Module Zero Development Board开发板（四）

Darth Nihilus2026-03-18 11:57

（七）Raspberry Pi Compute Module Zero Development Board 部署 PicoClaw

关于 PicoClaw

PicoClaw: 基于Go语言的超高效 AI 助手

🦐 PicoClaw 是一个受 nanobot 启发的超轻量级个人 AI 助手。它采用 Go 语言 从零重构，经历了一个"自举"过程------即由 AI Agent 自身驱动了整个架构迁移和代码优化。

⚡️ 极致轻量：可在 10 美元 的硬件上运行，内存占用不到 10MB。这意味着比 OpenClaw 节省 99% 的内存，比 Mac mini 便宜 98%！

主要特性

特性 描述
🪶 超轻量级 内存占用不到 10MB --- 比同类产品小 99%
💰 极低成本 可在 $10 硬件上运行 --- 比 Mac mini 便宜 98%
⚡️ 闪电启动 启动速度快 400 倍，即使在 0.6GHz 单核上也能 1 秒内启动
🌍 真正可移植 跨 RISC-V、ARM64 和 x86_64 的单二进制文件
🤖 AI 自举 95% 核心代码由 AI Agent 生成，经人机回环微调
💬 多通道支持 支持 Telegram、Discord、Slack、钉钉、飞书、企业微信、LINE、QQ 等

对比

OpenClaw NanoBot PicoClaw
语言 TypeScript Python Go
RAM 超过 1GB 超过 100MB 不到 10MB
启动时间 (0.8GHz) 超过 500s 超过 30s 不到 1s
成本 Mac Mini $599 ~$50 Linux 开发板 任意 Linux 开发板，低至 $10

架构图


（以上内容源自PicoClaw官方Github仓库：https://github.com/sipeed/picoclaw）
更多内容可以参考PicoClaw官方网站：https://picoclaw.io/

Raspberry Pi Compute Module Zero Development Board 安装 PicoClaw

操作系统选择

序号 操作系统 下载地址 是否可以配置PicoClaw
1 Raspberry Pi OS(Desktop) 64-bit-trixie (Debian 13) https://downloads.raspberrypi.com/raspios_arm64/images/raspios_arm64-2025-10-02/2025-10-01-raspios-trixie-arm64.img.xz 已验证
2 Raspberry Pi OS(Lite) 64-bit-trixie (Debian 13) https://downloads.raspberrypi.com/raspios_lite_arm64/images/raspios_lite_arm64-2025-10-02/2025-10-01-raspios-trixie-arm64-lite.img.xz 已验证
3 Raspberry Pi OS(Desktop) 32-bit-trixie (Debian 13) https://downloads.raspberrypi.com/raspios_armhf/images/raspios_armhf-2025-10-02/2025-10-01-raspios-trixie-armhf.img.xz 未验证
4 Raspberry Pi OS(Lite) 32-bit-trixie (Debian 13) https://downloads.raspberrypi.com/raspios_lite_armhf/images/raspios_lite_armhf-2025-10-02/2025-10-01-raspios-trixie-armhf-lite.img.xz 未验证

预编译二进制文件选择

从 Releases 页面 下载最新版本。所有版本打包为 .tar.gz（Linux/macOS/FreeBSD）或 .zip（Windows）。

平台 架构 下载
🐧 Linux x86_64 picoclaw_Linux_x86_64.tar.gz
🐧 Linux ARM64 picoclaw_Linux_arm64.tar.gz
🐧 Linux ARMv6（32 位） picoclaw_Linux_armv6.tar.gz
🐧 Linux RISC-V 64 picoclaw_Linux_riscv64.tar.gz
🐧 Linux LoongArch64 picoclaw_Linux_loong64.tar.gz
🍎 macOS ARM64 (Apple Silicon) picoclaw_Darwin_arm64.tar.gz
🍎 macOS x86_64 picoclaw_Darwin_x86_64.tar.gz
🪟 Windows x86_64 picoclaw_Windows_x86_64.zip
🪟 Windows ARM64 picoclaw_Windows_arm64.zip
😈 FreeBSD x86_64 picoclaw_Freebsd_x86_64.tar.gz
😈 FreeBSD ARM64 picoclaw_Freebsd_arm64.tar.gz
😈 FreeBSD ARMv6 picoclaw_Freebsd_armv6.tar.gz

一键安装 PicoClaw

bash 复制代码 
wget https://github.com/sipeed/picoclaw/releases/latest/download/picoclaw_Linux_arm64.tar.gz
tar -xzf picoclaw_Linux_arm64.tar.gz
./picoclaw onboard

██████╗ ██╗ ██████╗ ██████╗  ██████╗██╗      █████╗ ██╗    ██╗
██╔══██╗██║██╔════╝██╔═══██╗██╔════╝██║     ██╔══██╗██║    ██║
██████╔╝██║██║     ██║   ██║██║     ██║     ███████║██║ █╗ ██║
██╔═══╝ ██║██║     ██║   ██║██║     ██║     ██╔══██║██║███╗██║
██║     ██║╚██████╗╚██████╔╝╚██████╗███████╗██║  ██║╚███╔███╔╝
╚═╝     ╚═╝ ╚═════╝ ╚═════╝  ╚═════╝╚══════╝╚═╝  ╚═╝ ╚══╝╚══╝

Config already exists at /home/picoclaw/.picoclaw/config.json
Overwrite? (y/n):

显示上述内容即为安装成功。

Raspberry Pi Compute Module Zero Development Board 配置 PicoClaw

工作区布局

PicoClaw 将数据存储在工作区中（默认：~/.picoclaw/workspace）：

bash 复制代码 
~/.picoclaw/workspace/
├── sessions/          # 对话会话和历史
├── memory/           # 长期记忆 (MEMORY.md)
├── state/            # 持久化状态 (最后一次频道等)
├── cron/             # 定时任务数据库
├── skills/           # 自定义技能
├── AGENTS.md         # Agent 行为指南
├── HEARTBEAT.md      # 周期性任务提示词 (每 30 分钟检查一次)
├── IDENTITY.md       # Agent 身份设定
├── SOUL.md           # Agent 灵魂/性格
└── USER.md           # 用户偏好

模型配置

bash 复制代码 
sudo nano .picoclaw/config.json

#修改下述内容
  "model_list": [
    {
      "model_name": "ark-code-latest",
      "model": "volcengine/ark-code-latest",
      "api_key": "sk-your-volcengine-key"
    },
    {
      "model_name": "gpt-5.4",
      "model": "openai/gpt-5.4",
      "api_key": "sk-your-openai-key",
      "api_base": "https://api.openai.com/v1"
    },
    {
      "model_name": "claude-sonnet-4.6",
      "model": "anthropic/claude-sonnet-4.6",
      "api_key": "sk-ant-your-key",
      "api_base": "https://api.anthropic.com/v1"
    },
    {
      "model_name": "gemini",
      "model": "antigravity/gemini-2.0-flash",
      "auth_method": "oauth"
    },
    {
      "model_name": "deepseek",
      "model": "deepseek/deepseek-chat",
      "api_key": "sk-your-deepseek-key"
    },
    {
      "model_name": "loadbalanced-gpt-5.4",
      "model": "openai/gpt-5.4",
      "api_key": "sk-key1",
      "api_base": "https://api1.example.com/v1"
    },
    {
      "model_name": "loadbalanced-gpt-5.4",
      "model": "openai/gpt-5.4",
      "api_key": "sk-key2",
      "api_base": "https://api2.example.com/v1"
    }
  ],
  • 模型条目字段
字段 类型 必填 说明
model_name string 是 别名（在 agents.defaults.model_name 中引用）
model string 是 vendor/model-id 格式
api_key string 视情况 提供商 API Key
api_base string 否 覆盖默认 API 地址
auth_method string 否 认证方式（如 oauth）
proxy string 否 该模型 API 调用的 HTTP/SOCKS 代理
request_timeout int 否 请求超时时间（秒），默认 120
rpm int 否 速率限制 --- 每分钟请求数

聊天通道配置

bash 复制代码 
sudo nano .picoclaw/config.json

#修改下述内容
  "channels": {
    "telegram": {
      "enabled": false,
      "token": "YOUR_TELEGRAM_BOT_TOKEN",
      "base_url": "",
      "proxy": "",
      "allow_from": ["YOUR_USER_ID"],
      "reasoning_channel_id": ""
    },
    "discord": {
      "enabled": false,
      "token": "YOUR_DISCORD_BOT_TOKEN",
      "proxy": "",
      "allow_from": [],
      "group_trigger": {
        "mention_only": false
      },
      "reasoning_channel_id": ""
    },
    "qq": {
      "enabled": false,
      "app_id": "YOUR_QQ_APP_ID",
      "app_secret": "YOUR_QQ_APP_SECRET",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "maixcam": {
      "enabled": false,
      "host": "0.0.0.0",
      "port": 18790,
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "whatsapp": {
      "enabled": false,
      "bridge_url": "ws://localhost:3001",
      "use_native": false,
      "session_store_path": "",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "feishu": {
      "enabled": false,
      "app_id": "",
      "app_secret": "",
      "encrypt_key": "",
      "verification_token": "",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "dingtalk": {
      "enabled": false,
      "client_id": "YOUR_CLIENT_ID",
      "client_secret": "YOUR_CLIENT_SECRET",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "slack": {
      "enabled": false,
      "bot_token": "xoxb-YOUR-BOT-TOKEN",
      "app_token": "xapp-YOUR-APP-TOKEN",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "line": {
      "enabled": false,
      "channel_secret": "YOUR_LINE_CHANNEL_SECRET",
      "channel_access_token": "YOUR_LINE_CHANNEL_ACCESS_TOKEN",
      "webhook_path": "/webhook/line",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "onebot": {
      "enabled": false,
      "ws_url": "ws://127.0.0.1:3001",
      "access_token": "",
      "reconnect_interval": 5,
      "group_trigger_prefix": [],
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "wecom": {
      "enabled": false,
      "token": "YOUR_TOKEN",
      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
      "webhook_url": "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY",
      "webhook_path": "/webhook/wecom",
      "allow_from": [],
      "reply_timeout": 5,
      "reasoning_channel_id": ""
    },
    "wecom_app": {
      "enabled": false,
      "corp_id": "YOUR_CORP_ID",
      "corp_secret": "YOUR_CORP_SECRET",
      "agent_id": 1000002,
      "token": "YOUR_TOKEN",
      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
      "webhook_path": "/webhook/wecom-app",
      "allow_from": [],
      "reply_timeout": 5,
      "reasoning_channel_id": ""
    },
    "wecom_aibot": {
      "enabled": false,
      "token": "YOUR_TOKEN",
      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
      "webhook_path": "/webhook/wecom-aibot",
      "max_steps": 10,
      "welcome_message": "你好！我是你的 AI 助手，有什么可以帮你的吗？",
      "reasoning_channel_id": ""
    },
    "matrix": {
      "enabled": false,
      "homeserver": "https://matrix.org",
      "user_id": "@your-bot:matrix.org",
      "access_token": "YOUR_MATRIX_ACCESS_TOKEN",
      "device_id": "",
      "join_on_invite": true,
      "allow_from": [],
      "group_trigger": {
        "mention_only": true
      },
      "placeholder": {
        "enabled": true,
        "text": "正在思考..."
      },
      "reasoning_channel_id": ""
    }
  },

工具配置

bash 复制代码 
sudo nano .picoclaw/config.json

#修改下述内容
  "tools": {
    "web": {
      "brave": {
        "enabled": false,
        "api_key": "YOUR_BRAVE_API_KEY",
        "max_results": 5
      },
      "duckduckgo": {
        "enabled": true,
        "max_results": 5
      },
      "perplexity": {
        "enabled": false,
        "api_key": "pplx-xxx",
        "max_results": 5
      },
      "proxy": ""
    },

MCP配置

bash 复制代码 
sudo nano .picoclaw/config.json

#修改下述内容
    "mcp": {
      "enabled": false,
      "servers": {
        "context7": {
          "enabled": false,
          "type": "http",
          "url": "https://mcp.context7.com/mcp"
        },
        "filesystem": {
          "enabled": false,
          "command": "npx",
          "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
        },
        "github": {
          "enabled": false,
          "command": "npx",
          "args": ["-y", "@modelcontextprotocol/server-github"],
          "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_TOKEN" }
        }
      }
    },

心跳任务配置

bash 复制代码 
sudo nano .picoclaw/config.json

#修改下述内容
  "heartbeat": {
    "enabled": true,
    "interval": 30
  },
  • Agent 会每隔 30 分钟读取文件，并使用可用工具执行其中的任务。
  • 新建心跳任务
bash 复制代码 
sudo nano .picoclaw/workspace/HEARTBEAT.md

#添加心跳任务内容
# 周期任务
- 检查我的邮件中是否有重要消息
- 查看日历中即将到来的日程
- 查询今天的天气预报

安全沙箱

bash 复制代码 
sudo nano .picoclaw/config.json

#修改下述内容
{
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "restrict_to_workspace": true,
      "model_name": " ",
      "max_tokens": 32768,
      "max_tool_iterations": 50
    }
  },
配置项 默认值 说明
workspace ~/.picoclaw/workspace Agent 的工作目录
restrict_to_workspace true 将文件/命令访问限制在工作目录内
allow_read_outside_workspace false 即使开启了限制，也允许读取工作目录以外的文件

完整配置参考

bash 复制代码 
{
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "restrict_to_workspace": true,
      "model_name": "gpt-5.4",
      "max_tokens": 32768,
      "max_tool_iterations": 50
    }
  },

  "model_list": [
    {
      "model_name": "ark-code-latest",
      "model": "volcengine/ark-code-latest",
      "api_key": "sk-your-volcengine-key"
    },
    {
      "model_name": "gpt-5.4",
      "model": "openai/gpt-5.4",
      "api_key": "sk-your-openai-key",
      "api_base": "https://api.openai.com/v1"
    },
    {
      "model_name": "claude-sonnet-4.6",
      "model": "anthropic/claude-sonnet-4.6",
      "api_key": "sk-ant-your-key",
      "api_base": "https://api.anthropic.com/v1"
    },
    {
      "model_name": "gemini",
      "model": "antigravity/gemini-2.0-flash",
      "auth_method": "oauth"
    },
    {
      "model_name": "deepseek",
      "model": "deepseek/deepseek-chat",
      "api_key": "sk-your-deepseek-key"
    },
    {
      "model_name": "loadbalanced-gpt-5.4",
      "model": "openai/gpt-5.4",
      "api_key": "sk-key1",
      "api_base": "https://api1.example.com/v1"
    },
    {
      "model_name": "loadbalanced-gpt-5.4",
      "model": "openai/gpt-5.4",
      "api_key": "sk-key2",
      "api_base": "https://api2.example.com/v1"
    }
  ],

  "channels": {
    "telegram": {
      "enabled": false,
      "token": "YOUR_TELEGRAM_BOT_TOKEN",
      "base_url": "",
      "proxy": "",
      "allow_from": ["YOUR_USER_ID"],
      "reasoning_channel_id": ""
    },
    "discord": {
      "enabled": false,
      "token": "YOUR_DISCORD_BOT_TOKEN",
      "proxy": "",
      "allow_from": [],
      "group_trigger": {
        "mention_only": false
      },
      "reasoning_channel_id": ""
    },
    "qq": {
      "enabled": false,
      "app_id": "YOUR_QQ_APP_ID",
      "app_secret": "YOUR_QQ_APP_SECRET",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "maixcam": {
      "enabled": false,
      "host": "0.0.0.0",
      "port": 18790,
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "whatsapp": {
      "enabled": false,
      "bridge_url": "ws://localhost:3001",
      "use_native": false,
      "session_store_path": "",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "feishu": {
      "enabled": false,
      "app_id": "",
      "app_secret": "",
      "encrypt_key": "",
      "verification_token": "",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "dingtalk": {
      "enabled": false,
      "client_id": "YOUR_CLIENT_ID",
      "client_secret": "YOUR_CLIENT_SECRET",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "slack": {
      "enabled": false,
      "bot_token": "xoxb-YOUR-BOT-TOKEN",
      "app_token": "xapp-YOUR-APP-TOKEN",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "line": {
      "enabled": false,
      "channel_secret": "YOUR_LINE_CHANNEL_SECRET",
      "channel_access_token": "YOUR_LINE_CHANNEL_ACCESS_TOKEN",
      "webhook_path": "/webhook/line",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "onebot": {
      "enabled": false,
      "ws_url": "ws://127.0.0.1:3001",
      "access_token": "",
      "reconnect_interval": 5,
      "group_trigger_prefix": [],
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "wecom": {
      "enabled": false,
      "token": "YOUR_TOKEN",
      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
      "webhook_url": "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY",
      "webhook_path": "/webhook/wecom",
      "allow_from": [],
      "reply_timeout": 5,
      "reasoning_channel_id": ""
    },
    "wecom_app": {
      "enabled": false,
      "corp_id": "YOUR_CORP_ID",
      "corp_secret": "YOUR_CORP_SECRET",
      "agent_id": 1000002,
      "token": "YOUR_TOKEN",
      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
      "webhook_path": "/webhook/wecom-app",
      "allow_from": [],
      "reply_timeout": 5,
      "reasoning_channel_id": ""
    },
    "wecom_aibot": {
      "enabled": false,
      "token": "YOUR_TOKEN",
      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
      "webhook_path": "/webhook/wecom-aibot",
      "max_steps": 10,
      "welcome_message": "你好！我是你的 AI 助手，有什么可以帮你的吗？",
      "reasoning_channel_id": ""
    },
    "matrix": {
      "enabled": false,
      "homeserver": "https://matrix.org",
      "user_id": "@your-bot:matrix.org",
      "access_token": "YOUR_MATRIX_ACCESS_TOKEN",
      "device_id": "",
      "join_on_invite": true,
      "allow_from": [],
      "group_trigger": {
        "mention_only": true
      },
      "placeholder": {
        "enabled": true,
        "text": "正在思考..."
      },
      "reasoning_channel_id": ""
    }
  },

  "tools": {
    "web": {
      "brave": {
        "enabled": false,
        "api_key": "YOUR_BRAVE_API_KEY",
        "max_results": 5
      },
      "duckduckgo": {
        "enabled": true,
        "max_results": 5
      },
      "perplexity": {
        "enabled": false,
        "api_key": "pplx-xxx",
        "max_results": 5
      },
      "proxy": ""
    },
    "mcp": {
      "enabled": false,
      "servers": {
        "context7": {
          "enabled": false,
          "type": "http",
          "url": "https://mcp.context7.com/mcp"
        },
        "filesystem": {
          "enabled": false,
          "command": "npx",
          "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
        },
        "github": {
          "enabled": false,
          "command": "npx",
          "args": ["-y", "@modelcontextprotocol/server-github"],
          "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_TOKEN" }
        }
      }
    },
    "cron": {
      "exec_timeout_minutes": 5
    },
    "exec": {
      "enable_deny_patterns": true,
      "custom_deny_patterns": [],
      "custom_allow_patterns": []
    },
    "skills": {
      "registries": {
        "clawhub": {
          "enabled": true,
          "base_url": "https://clawhub.ai",
          "search_path": "/api/v1/search",
          "skills_path": "/api/v1/skills",
          "download_path": "/api/v1/download"
        }
      }
    }
  },

  "heartbeat": {
    "enabled": true,
    "interval": 30
  },

  "devices": {
    "enabled": false,
    "monitor_usb": true
  },

  "gateway": {
    "host": "127.0.0.1",
    "port": 18790
  }
}
  • 字段说明
    • agents.defaults
字段 类型 默认值 说明
workspace string ~/.picoclaw/workspace Agent 工作目录（受 PICOCLAW_HOME 影响）
restrict_to_workspace bool true 限制文件/命令访问在工作目录内
allow_read_outside_workspace bool false 允许读取工作目录以外的文件（restrict_to_workspace 为 true 时生效）
model_name string --- 默认模型名（必须在 model_list 中存在）
model string --- 已废弃：请使用 model_name
model_fallbacks array [] 备用模型名列表，主模型失败时按顺序尝试
max_tokens int 32768 每次响应最大 token 数
temperature float --- LLM 温度（省略则使用提供商默认值）
max_tool_iterations int 50 每次请求最多工具调用次数
max_media_size int 20971520 最大媒体文件大小（字节），默认 20MB
image_model string --- 图片生成使用的模型名
image_model_fallbacks array [] 图片生成备用模型
routing object --- 智能模型路由设置（见下方）

routing

字段 类型 默认值 说明
enabled bool false 启用智能模型路由
light_model string --- 用于简单任务的模型名（需在 model_list 中存在）
threshold float --- 复杂度评分阈值 [0,1]；评分 >= 阈值使用主模型，低于阈值使用 light_model

启用后，PicoClaw 会根据消息的结构特征（长度、代码块、工具调用历史、对话深度、附件）对每条消息评分，将简单消息路由到更轻量/低成本的模型。

    • model_list[]
字段 类型 必填 说明
model_name string 是 别名（在 agents.defaults.model_name 中引用）
model string 是 vendor/model-id 格式
api_key string 视情况 提供商 API Key
api_base string 否 覆盖默认 API 地址
auth_method string 否 认证方式（如 oauth）
proxy string 否 该模型的 HTTP/SOCKS 代理
request_timeout int 否 请求超时时间（秒），默认 120
rpm int 否 速率限制（每分钟请求数）
max_tokens_field string 否 覆盖 API 请求中的 max tokens 字段名
connect_mode string 否 连接模式覆盖
workspace string 否 模型级工作目录覆盖
thinking_level string 否 扩展思考级别：off、low、medium、high、xhigh 或 adaptive
    • gateway
字段 类型 默认值 说明
host string 127.0.0.1 网关监听地址
port int 18790 网关监听端口

设置 host: "0.0.0.0" 可让网关对外开放。

  • 通用渠道字段

所有渠道均支持以下字段：

字段 类型 说明
enabled bool 启用/禁用该渠道
allow_from array 允许使用机器人的用户 ID（空数组 = 允许所有人）
reasoning_channel_id string 专用于输出推理过程的频道/群组 ID
group_trigger object 群聊触发设置（见下方）
placeholder object 占位消息设置（见下方）
typing object 输入状态指示器设置（见下方）
    • group_trigger
字段 类型 说明
mention_only bool 仅在群聊中被 @ 时响应
prefixes array 群聊中触发机器人的关键词前缀
    • placeholder
字段 类型 说明
enabled bool 启用占位消息
text string 处理期间显示的占位文本（如"正在思考..."）

支持的通道：飞书、Slack、Matrix。

    • typing
字段 类型 说明
enabled bool 处理期间显示"正在输入"状态

支持的通道：Slack、Matrix。

Raspberry Pi Compute Module Zero Development Board 使用 PicoClaw

命令 描述
picoclaw onboard 初始化配置和工作目录
picoclaw agent -m "..." 单次对话
picoclaw agent 交互式对话模式
picoclaw gateway 启动网关（用于聊天应用）
picoclaw status 显示状态
picoclaw cron list 列出所有定时任务
picoclaw cron add ... 添加定时任务

Raspberry Pi Compute Module Zero Development Board 使用 PicoClaw WEB管理

Raspberry Pi Compute Module Zero Development Board 输入；
bash 复制代码 
./picoclaw-launcher -public


██████╗ ██╗ ██████╗ ██████╗  ██████╗██╗      █████╗ ██╗    ██╗
██╔══██╗██║██╔════╝██╔═══██╗██╔════╝██║     ██╔══██╗██║    ██║
██████╔╝██║██║     ██║   ██║██║     ██║     ███████║██║ █╗ ██║
██╔═══╝ ██║██║     ██║   ██║██║     ██║     ██╔══██║██║███╗██║
██║     ██║╚██████╗╚██████╔╝╚██████╗███████╗██║  ██║╚███╔███╔╝
╚═╝     ╚═╝ ╚═════╝ ╚═════╝  ╚═════╝╚══════╝╚═╝  ╚═╝ ╚══╝╚══╝

  Open the following URL in your browser:

    >> http://localhost:18800 <<
    >> http://192.168.2.200:18800 <<

2026/03/17 00:00:00 Started picoclaw gateway (PID: 2291) from /home/picoclaw/picoclaw_Linux_arm64/picoclaw
2026/03/17 00:00:00 Gateway auto-started (PID: 2291)
浏览器中输入"http://IP:18800"，如下图所示即为成功。

Raspberry Pi Compute Module Zero Development Board 使用 PicoClaw QQ 管理

Raspberry Pi Compute Module Zero Development Board 输入；
bash 复制代码 
./picoclaw gateway


██████╗ ██╗ ██████╗ ██████╗  ██████╗██╗      █████╗ ██╗    ██╗
██╔══██╗██║██╔════╝██╔═══██╗██╔════╝██║     ██╔══██╗██║    ██║
██████╔╝██║██║     ██║   ██║██║     ██║     ███████║██║ █╗ ██║
██╔═══╝ ██║██║     ██║   ██║██║     ██║     ██╔══██║██║███╗██║
██║     ██║╚██████╗╚██████╔╝╚██████╗███████╗██║  ██║╚███╔███╔╝
╚═╝     ╚═╝ ╚═════╝ ╚═════╝  ╚═════╝╚══════╝╚═╝  ╚═╝ ╚══╝╚══╝

2026/03/17 00:00:00 [2026-03-17T00:00:00Z] [INFO] agent: Created implicit main agent (no agents.list configured)

📦 Agent Status:
  • Tools: 15 loaded
  • Skills: 6/6 available
在手机QQ中选择对应QQ机器人输入内容，如下图所示即为成功。
相关推荐
Xzq2105092 小时前
Reactor模式
linux·网络
小鸡吃米…2 小时前
Python 中的并发 —— 进程池
linux·服务器·开发语言·python
星辰引路-Lefan2 小时前
全平台 Docker 部署 CPA(CLIProxyAPI Plus) 灵活定制指南 (Linux/Windows)——接入Codex
linux·windows·docker·ai·ai编程
历程里程碑2 小时前
40 UDP - 2 C++实现英汉词典查询服务
linux·开发语言·数据结构·c++·ide·c#·vim
程序设计实验室2 小时前
别再手动复制SSH公钥了，Linux服务器一键从GitHub快速导入公钥
linux
我不是程序猿儿2 小时前
【嵌入式】外部中断的学习小坑记录
单片机·嵌入式硬件·学习
学嵌入式的小杨同学2 小时前
STM32 进阶封神之路（十三）：空气质量传感器实战 ——KQM6600 模块从协议到代码（串口通信 + 数据解析）
c++·stm32·单片机·嵌入式硬件·架构·硬件架构·嵌入式实时数据库
雾岛听蓝2 小时前
动静态库原理与ELF文件详解
linux·经验分享·笔记
枕布响丸辣2 小时前
Nginx 安全防护与 HTTPS 部署实战
linux·运维·服务器·系统安全
热门推荐
01GitHub 镜像站点02Qwen3.5 开源全解析：从 0.8B 到 397B，代际升级 + 全场景选型指南03OpenClaw 使用和管理 MCP 完全指南04UV安装并设置国内源05OpenClaw Control UI安全上下文访问配置06OpenClaw macOS 完整安装与本地模型配置教程（实战版）07本地部署 OpenClaw + DeepSeek-R1 完全指南08Claude Code + GLM4.7 避坑指南：解决 Unable to connect to Anthropic services09小黑课堂计算机二级WPSoffice题库软件下载安装教程（2026年3月最新版）10让 Trae IDE 智能体 “读懂”文档 Excel+PDF+DOCX ：mcp-documents-reader 工具使用指南