OpenClaw 是一個開源的個人 AI 助手平台,支援通過多種訊息渠道與 AI 互動。通過配置可接入阿里雲百鍊平台上的 AI 模型,支援隨用隨付、Coding Plan、Token Plan 個人版、Token Plan 團隊版四種接入方式。
安裝 OpenClaw
OpenClaw 需要 Node.js 22.19.0 或更高版本。可通過以下命令檢查 Node.js 版本:
node --version
如果未安裝或版本過低,請訪問 Node.js 官網下載安裝。
macOS / Linux
推薦使用官方安裝指令碼:
curl -fsSL https://openclaw.ai/install.sh | bash
或通過 npm 全域安裝:
npm install -g openclaw@latest
Windows
在 PowerShell 中執行:
iwr -useb https://openclaw.ai/install.ps1 | iex
或通過 npm 全域安裝:
npm install -g openclaw@latest
首次安裝後,OpenClaw 會自動啟動設定精靈,完成初始設定。也可以手動執行openclaw onboard命令進行配置。
配置項 | 建議配置 |
|---|---|
I understand this is powerful and inherently risky. Continue? | 選擇 Yes |
Onboarding mode | 選擇 QuickStart |
Model/auth provider | 選擇 Skip for now(稍後配置百鍊模型) |
Filter models by provider | 選擇 All providers |
Default model | 選擇 Keep current |
Select channel (QuickStart) | 選擇 Skip for now(稍後配置渠道) |
Configure skills now? (recommended) | 選擇 No |
Enable hooks? | 按空格鍵選中選項,按斷行符號鍵進入下一步 |
How do you want to hatch your bot? | 選擇 Do this later |
配置接入憑證
Token Plan 個人版
配置項 | 說明 |
|---|---|
API Key | Token Plan 個人版專屬 API Key |
Base URL |
|
可用模型 | Token Plan 個人版支援的模型 |
設定檔位於 ~/.openclaw/openclaw.json,OpenClaw 啟動時會自動讀取。
說明樣本禁用了網關鑒權(auth.mode: none),僅適合單機本地使用。如需共用或遠端存取,請運行 openclaw doctor --fix 啟用 token 鑒權。
首次配置:複製以下內容到設定檔,將 YOUR_API_KEY 替換為 Token Plan 個人版 API Key。
已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian-token-plan": {
"baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.8-max",
"name": "qwen3.8-max",
"reasoning": true,
"input": ["text", "image"],
"contextWindow": 983616,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.7-max",
"name": "qwen3.7-max",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.7-plus",
"name": "qwen3.7-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-flash",
"name": "qwen3.6-flash",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5.2",
"name": "glm-5.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-pro-0813",
"name": "deepseek-v4-pro-0813",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-flash-0731",
"name": "deepseek-v4-flash-0731",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 393216,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian-token-plan/qwen3.8-max"
},
"models": {
"bailian-token-plan/qwen3.8-max": {},
"bailian-token-plan/qwen3.7-max": {},
"bailian-token-plan/qwen3.7-plus": {},
"bailian-token-plan/qwen3.6-flash": {},
"bailian-token-plan/glm-5.2": {},
"bailian-token-plan/deepseek-v4-pro": {},
"bailian-token-plan/deepseek-v4-pro-0813": {},
"bailian-token-plan/deepseek-v4-flash-0731": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
Token Plan 團隊版
配置項 | 說明 |
|---|---|
API Key | Token Plan 團隊版專屬 API Key |
Base URL |
|
可用模型 | Token Plan 團隊版支援的模型 |
設定檔位於 ~/.openclaw/openclaw.json,OpenClaw 啟動時會自動讀取。
說明樣本禁用了網關鑒權(auth.mode: none),僅適合單機本地使用。如需共用或遠端存取,請運行 openclaw doctor --fix 啟用 token 鑒權。
方式一:終端方式
- 開啟設定檔
nano ~/.openclaw/openclaw.json
-
寫入配置
首次配置:複製以下內容到設定檔,將
YOUR_API_KEY替換為 Token Plan 團隊版 API Key。已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian-token-plan": {
"baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.8-max",
"name": "qwen3.8-max",
"reasoning": true,
"input": ["text", "image"],
"contextWindow": 983616,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.7-max",
"name": "qwen3.7-max",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.7-plus",
"name": "qwen3.7-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-flash",
"name": "qwen3.6-flash",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-pro-0813",
"name": "deepseek-v4-pro-0813",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-flash-0731",
"name": "deepseek-v4-flash-0731",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 393216,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "kimi-k2.7-code",
"name": "kimi-k2.7-code",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "kimi-k2.6",
"name": "kimi-k2.6",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "kimi-k2.5",
"name": "kimi-k2.5",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5.2",
"name": "glm-5.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5.1",
"name": "glm-5.1",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 204800,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian-token-plan/qwen3.8-max"
},
"models": {
"bailian-token-plan/qwen3.8-max": {},
"bailian-token-plan/qwen3.7-max": {},
"bailian-token-plan/qwen3.7-plus": {},
"bailian-token-plan/qwen3.6-plus": {},
"bailian-token-plan/qwen3.6-flash": {},
"bailian-token-plan/deepseek-v4-pro": {},
"bailian-token-plan/deepseek-v4-pro-0813": {},
"bailian-token-plan/deepseek-v4-flash": {},
"bailian-token-plan/deepseek-v4-flash-0731": {},
"bailian-token-plan/deepseek-v3.2": {},
"bailian-token-plan/kimi-k2.7-code": {},
"bailian-token-plan/kimi-k2.6": {},
"bailian-token-plan/kimi-k2.5": {},
"bailian-token-plan/glm-5.2": {},
"bailian-token-plan/glm-5.1": {},
"bailian-token-plan/glm-5": {},
"bailian-token-plan/MiniMax-M2.5": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
-
儲存並退出
按
Ctrl+X,按Y確認儲存,按Enter確認檔案名稱。 -
使配置生效
運行以下命令重啟網關,使配置生效。
openclaw gateway restart
方式二:Web UI 方式
-
啟動 Web UI
在終端運行以下命令啟動 Web UI:
openclaw dashboard
在瀏覽器開啟的頁面中,單擊左側菜單 設定,將編輯器模式從 Form 切換為 Raw。 2. 寫入配置
首次配置:複製以下內容到設定檔,將 YOUR_API_KEY 替換為 Token Plan 團隊版 API Key。
已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian-token-plan": {
"baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.8-max",
"name": "qwen3.8-max",
"reasoning": true,
"input": ["text", "image"],
"contextWindow": 983616,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.7-max",
"name": "qwen3.7-max",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.7-plus",
"name": "qwen3.7-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-flash",
"name": "qwen3.6-flash",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-pro-0813",
"name": "deepseek-v4-pro-0813",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-flash-0731",
"name": "deepseek-v4-flash-0731",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 393216,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "kimi-k2.7-code",
"name": "kimi-k2.7-code",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "kimi-k2.6",
"name": "kimi-k2.6",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "kimi-k2.5",
"name": "kimi-k2.5",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5.2",
"name": "glm-5.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5.1",
"name": "glm-5.1",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 204800,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian-token-plan/qwen3.8-max"
},
"models": {
"bailian-token-plan/qwen3.8-max": {},
"bailian-token-plan/qwen3.7-max": {},
"bailian-token-plan/qwen3.7-plus": {},
"bailian-token-plan/qwen3.6-plus": {},
"bailian-token-plan/qwen3.6-flash": {},
"bailian-token-plan/deepseek-v4-pro": {},
"bailian-token-plan/deepseek-v4-pro-0813": {},
"bailian-token-plan/deepseek-v4-flash": {},
"bailian-token-plan/deepseek-v4-flash-0731": {},
"bailian-token-plan/deepseek-v3.2": {},
"bailian-token-plan/kimi-k2.7-code": {},
"bailian-token-plan/kimi-k2.6": {},
"bailian-token-plan/kimi-k2.5": {},
"bailian-token-plan/glm-5.2": {},
"bailian-token-plan/glm-5.1": {},
"bailian-token-plan/glm-5": {},
"bailian-token-plan/MiniMax-M2.5": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
-
儲存並應用
先單擊 Save 按鈕將配置寫入磁碟,再單擊 Apply 按鈕重啟網關使配置生效。
Coding Plan
配置項 | 說明 |
|---|---|
API Key | Coding Plan 專屬 API Key,格式為 |
Base URL | |
可用模型 | Coding Plan 支援的模型 |
設定檔位於 ~/.openclaw/openclaw.json,OpenClaw 啟動時會自動讀取。
說明樣本禁用了網關鑒權(auth.mode: none),僅適合單機本地使用。如需共用或遠端存取,請運行 openclaw doctor --fix 啟用 token 鑒權。
方式一:終端方式
- 開啟設定檔
nano ~/.openclaw/openclaw.json
-
寫入配置
首次配置:複製以下內容到設定檔,將
YOUR_API_KEY替換為 Coding Plan API Key。已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian-coding-plan": {
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.7-plus",
"name": "qwen3.7-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.5-plus",
"name": "qwen3.5-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3-max-2026-01-23",
"name": "qwen3-max-2026-01-23",
"reasoning": false,
"input": ["text"],
"contextWindow": 262144,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3-coder-next",
"name": "qwen3-coder-next",
"reasoning": false,
"input": ["text"],
"contextWindow": 262144,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "qwen3-coder-plus",
"name": "qwen3-coder-plus",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 204800,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-4.7",
"name": "glm-4.7",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "kimi-k2.5",
"name": "kimi-k2.5",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian-coding-plan/qwen3.7-plus"
},
"models": {
"bailian-coding-plan/qwen3.7-plus": {},
"bailian-coding-plan/qwen3.6-plus": {},
"bailian-coding-plan/qwen3.5-plus": {},
"bailian-coding-plan/qwen3-max-2026-01-23": {},
"bailian-coding-plan/qwen3-coder-next": {},
"bailian-coding-plan/qwen3-coder-plus": {},
"bailian-coding-plan/MiniMax-M2.5": {},
"bailian-coding-plan/glm-5": {},
"bailian-coding-plan/glm-4.7": {},
"bailian-coding-plan/kimi-k2.5": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
-
儲存並退出
按
Ctrl+X,按Y確認儲存,按Enter確認檔案名稱。 -
使配置生效
運行以下命令重啟網關,使配置生效。
openclaw gateway restart
方式二:Web UI 方式
-
啟動 Web UI
在終端運行以下命令啟動 Web UI:
openclaw dashboard
在瀏覽器開啟的頁面中,單擊左側菜單 設定,將編輯器模式從 Form 切換為 Raw。 2. 寫入配置
首次配置:複製以下內容到設定檔,將 YOUR_API_KEY 替換為 Coding Plan API Key。
已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian-coding-plan": {
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.7-plus",
"name": "qwen3.7-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3.5-plus",
"name": "qwen3.5-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3-max-2026-01-23",
"name": "qwen3-max-2026-01-23",
"reasoning": false,
"input": ["text"],
"contextWindow": 262144,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "qwen3-coder-next",
"name": "qwen3-coder-next",
"reasoning": false,
"input": ["text"],
"contextWindow": 262144,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "qwen3-coder-plus",
"name": "qwen3-coder-plus",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 204800,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "glm-4.7",
"name": "glm-4.7",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "kimi-k2.5",
"name": "kimi-k2.5",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian-coding-plan/qwen3.7-plus"
},
"models": {
"bailian-coding-plan/qwen3.7-plus": {},
"bailian-coding-plan/qwen3.6-plus": {},
"bailian-coding-plan/qwen3.5-plus": {},
"bailian-coding-plan/qwen3-max-2026-01-23": {},
"bailian-coding-plan/qwen3-coder-next": {},
"bailian-coding-plan/qwen3-coder-plus": {},
"bailian-coding-plan/MiniMax-M2.5": {},
"bailian-coding-plan/glm-5": {},
"bailian-coding-plan/glm-4.7": {},
"bailian-coding-plan/kimi-k2.5": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
-
儲存並應用
先單擊 Save 按鈕將配置寫入磁碟,再單擊 Apply 按鈕重啟網關使配置生效。
隨用隨付
配置項 | 說明 |
|---|---|
API Key | 阿里雲百鍊 API Key,格式為 |
Base URL | 請確保 Base URL、API Key 和模型歸屬同一地區,並將
|
可用模型 | 填入模型廣場中支援的模型 |
以下配置以華北2(北京)地區為例,如使用其他地區請替換 baseUrl 為上表中對應地區的 URL。
設定檔位於 ~/.openclaw/openclaw.json,OpenClaw 啟動時會自動讀取。
說明樣本禁用了網關鑒權(auth.mode: none),僅適合單機本地使用。如需共用或遠端存取,請運行 openclaw doctor --fix 啟用 token 鑒權。
方式一:終端方式
- 開啟設定檔
nano ~/.openclaw/openclaw.json
-
寫入配置
首次配置:複製以下內容到設定檔,將
YOUR_API_KEY替換為百鍊 API Key。已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian": {
"baseUrl": "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 204800,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian/qwen3.6-plus"
},
"models": {
"bailian/qwen3.6-plus": {},
"bailian/MiniMax-M2.5": {},
"bailian/glm-5": {},
"bailian/deepseek-v3.2": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
-
儲存並退出
按
Ctrl+X,按Y確認儲存,按Enter確認檔案名稱。 -
使配置生效
運行以下命令重啟網關,使配置生效。
openclaw gateway restart
方式二:Web UI 方式
-
啟動 Web UI
在終端運行以下命令啟動 Web UI:
openclaw dashboard
在瀏覽器開啟的頁面中,單擊左側菜單 設定,將編輯器模式從 Form 切換為 Raw。 2. 寫入配置
首次配置:複製以下內容到設定檔,將 YOUR_API_KEY 替換為百鍊 API Key。
已有配置:若需保留已有配置,請勿直接全量替換,詳見已有配置如何安全修改。
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-02-03T08:20:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"bailian": {
"baseUrl": "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1000000,
"maxTokens": 65536,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": false,
"input": ["text"],
"contextWindow": 204800,
"maxTokens": 131072,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
},
{
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"reasoning": false,
"input": ["text"],
"contextWindow": 163840,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"compat": { "thinkingFormat": "openai" }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "bailian/qwen3.6-plus"
},
"models": {
"bailian/qwen3.6-plus": {},
"bailian/MiniMax-M2.5": {},
"bailian/glm-5": {},
"bailian/deepseek-v3.2": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}
-
儲存並應用
先單擊 Save 按鈕將配置寫入磁碟,再單擊 Apply 按鈕重啟網關使配置生效。
接入訊息渠道
步驟一:安裝 WhatsApp 外掛程式
WhatsApp 渠道通過外掛程式方式接入,執行以下命令安裝外掛程式:
openclaw plugins install @openclaw/whatsapp
步驟二:配置 WhatsApp 渠道
在 OpenClaw 對話中輸入以下內容,OpenClaw 會詢問手機號碼(需使用 E.164 格式,即 + 號加國家代碼加手機號),然後自動將號碼填入配置並完成設定。
請幫我配置 WhatsApp 渠道。請先詢問My Phone號碼,然後將號碼自動填入以下配置中的 allowFrom 和 groupAllowFrom 欄位,完成配置。
{
"channels": {
"whatsapp": {
"dmPolicy": "pairing",
"allowFrom": ["<phone_number>"],
"groupPolicy": "allowlist",
"groupAllowFrom": ["<phone_number>"]
}
}
}
說明建議使用單獨的手機號運行 WhatsApp 渠道,避免機器人響應日常聊天中的訊息。如果使用日常聊天的手機號,可在 OpenClaw 對話中輸入開啟 selfChatMode,機器人將僅在給自己發訊息的對話中響應,不影響其他聊天。
步驟三:關聯 WhatsApp
- 執行以下命令啟動 WhatsApp 關聯流程,終端會顯示二維碼。
openclaw channels login --channel whatsapp
- 開啟手機 WhatsApp,掃描終端中的二維碼完成關聯。
- 重啟網關。
openclaw gateway restart
步驟四:測試
- 執行以下命令檢查 WhatsApp 渠道狀態。
openclaw status
在 Channels 部分,WhatsApp 應顯示為 ON 且狀態為 OK。
2. 在 WhatsApp 中給自己發送一條訊息,驗證機器人是否正常響應。
Telegram
-
通過 BotFather 建立機器人
發送
/newbot命令,按提示輸入機器人名稱和使用者名稱(使用者名稱必須以bot結尾),複製並儲存返回的 Bot Token(格式為:123456789:ABCdefGHIjklMNOpqrsTUVwxyz)。 -
在 OpenClaw 對話中輸入如下內容,並將 xxxx 替換為實際的 Bot Token。OpenClaw 會自動完成配置。
請幫我配置Telegram,配置項如下,我的Bot Token是xxxx。
{
"channels": {
"telegram": {
"enabled": true,
"botToken": "xxxx",
"dmPolicy": "pairing"
}
}
}
- 配置完成後,重啟網關。
openclaw gateway restart
- 在 Telegram 中發送訊息給機器人,首次發送訊息會收到配對碼。
- 在終端執行以下命令,將 xxx 替換為實際的配對碼。
openclaw pairing approve telegram xxx
Discord
步驟一:建立 Discord 應用和機器人
-
建立 Discord 應用
進入 Discord Developer Portal,單擊 New Application,輸入應用程式名稱,然後單擊 Create。
-
建立機器人並開啟許可權
-
在左側導覽列單擊 Bot,設定機器人使用者名稱。
-
在 Bot 頁面向下滾動到 Privileged Gateway Intents,開啟以下許可權:
- Message Content Intent
- Server Members Intent
- Presence Intent
完成後單擊 Save Changes。
-
-
擷取 Bot Token
在 Bot 頁面頂部,單擊 Reset Token 產生令牌,複製並妥善儲存。此令牌僅顯示一次。
-
添加機器人到伺服器
-
在左側導覽列單擊 OAuth2,向下滾動到 OAuth2 URL Generator。
-
在 Scopes 中勾選
bot和applications.commands。 -
在下方出現的 Bot Permissions 中勾選以下許可權:
- View Channels
- Send Messages
- Read Message History
- Embed Links
- Attach Files
-
複製頁面底部產生的 URL,在瀏覽器中開啟,選擇目標伺服器並單擊 Continue 完成添加。
-
步驟二:在 OpenClaw 中配置 Discord
- 在運行 OpenClaw 的機器上,設定 Bot Token 環境變數。
export DISCORD_BOT_TOKEN="YOUR_BOT_TOKEN"
- 執行以下命令完成 Discord 配置。
openclaw config set channels.discord.token --ref-provider default --ref-source env --ref-id DISCORD_BOT_TOKEN
openclaw config set channels.discord.enabled true --strict-json
- 重啟網關使配置生效。
openclaw gateway restart
步驟三:配對與測試
- 在 Discord 中向機器人發送私信,首次發送會收到配對碼(Pairing Code)。
- 在終端執行以下命令完成配對,將 xxx 替換為實際的配對碼。
openclaw pairing approve discord xxx
說明配對碼有效期間為 1 小時,到期需重新發送訊息擷取新的配對碼。
- 執行以下命令檢查 Discord 渠道狀態。
openclaw status
在 Channels 部分,Discord 應顯示為 ON 且狀態為 OK。
4. 在 Discord 中發送訊息進行測試。
常見命令
命令 | 說明 | 樣本 |
|---|---|---|
/help | 顯示可用命令的快速摘要。 | /help |
/status | 查看當前模型、會話、網關等狀態資訊。 | /status |
/model <模型名稱> | 切換當前會話使用的模型。 | /model qwen3.7-max |
/new | 開始一個新會話。 | /new |
/compact | 壓縮對話歷史,釋放上下文視窗空間。 | /compact |
/think <層級> | 設定思考(推理)深度層級,可選 off、low、medium、high 等。 | /think high |
/skills | 展示全部可用的 Skill。 | /skills |
使用案例
案例一:X(Twitter)自動營運
通過 OpenClaw 可自動化營運 X (Twitter) 帳號,支援發帖、回複、搜尋、時間軸瀏覽等操作。
配置步驟
- 在終端執行以下命令安裝 twitter-cli。
uv tool install twitter-cli
- 在 OpenClaw 對話中輸入以下指令,自動完成 Skill 安裝。
Install this skill: https://github.com/public-clis/twitter-cli
- 安裝完成後,返回終端並重啟網關使 Skill 生效。
openclaw gateway restart
- 驗證 Skill 是否安裝成功。
openclaw skills list
-
twitter-cli 使用瀏覽器 Cookie 進行認證。請確保已在支援的瀏覽器(Chrome、Edge、Firefox、Arc 或 Brave)中登入 x.com,twitter-cli 會自動提取 Cookie。
也可以通過環境變數手動設定認證資訊:
export TWITTER_AUTH_TOKEN="your_auth_token"
export TWITTER_CT0="your_ct0_token"
說明Cookie 擷取方式:在瀏覽器中開啟 x.com,開啟開發人員工具,切換到 Application 面板,在 Cookies 中找到 auth_token 和 ct0 的值。
樣本一:自動發布文章
在 OpenClaw 對話中輸入查看 Sam Altman 最近的推文,總結要點後幫我發一條推文談談我的看法,OpenClaw 會自動擷取動態、分析內容並發布。
樣本二:搜尋熱門話題
輸入幫我搜尋昨天關於 harness engineering 的推文,OpenClaw 會搜尋相關推文並總結要點。
案例二:YouTube 視頻分析與下載
通過OpenClaw 可以搜尋 YouTube 視頻、提取視頻資訊並下載視頻,支援按關鍵詞搜尋、按日期排序、批量擷取視頻中繼資料等操作。
配置步驟
- 在終端執行以下命令安裝 yt-dlp。
pip install yt-dlp
- 驗證安裝。
yt-dlp --version
- (可選)配置 Cookie 認證。如果需要訪問年齡限制、會員專屬或私人視頻,需要配置 YouTube Cookie。確保已在瀏覽器中登入 youtube.com,然後在 OpenClaw 對話中輸入:
我需要配置 YouTube 的 Cookie 認證,請使用 yt-dlp 從我的瀏覽器中提取 YouTube 的 Cookie
安裝完成後,即可在 OpenClaw 對話中直接使用,OpenClaw 會自動調用 yt-dlp 命令執行視頻相關操作。
樣本一:視頻內容總結
在 OpenClaw 對話中輸入幫我總結這個視頻的主要內容:https://www.youtube.com/watch?v=XRgGFQ0EgM0,OpenClaw 會提取視頻資訊並產生內容摘要。
樣本二:視頻下載
在 OpenClaw 對話中輸入幫我下載這個視頻:https://www.youtube.com/watch?v=XRgGFQ0EgM0,OpenClaw 會調用 yt-dlp 將視頻下載到本地。
案例三:定時推送 AI 新聞
通過 OpenClaw 的 Cron 定時任務功能,每天自動抓取最新 AI 新聞並推送到 Discord(Cron 定時任務支援 discord 和 telegram 渠道)。
配置步驟
- 在終端執行以下命令:
openclaw cron add \
--name "ai-daily-news" \
--cron "0 9 * * *" \
--tz "UTC" \
--message "Please visit https://techcrunch.com/category/artificial-intelligence/ to get today's AI news. Summarize the top 10 most important AI stories in a concise list format, each with a title and a one-sentence summary in English." \
--channel discord \
--announce
參數說明如下:
| 參數 | 說明 | | --- | --- | | --name | 任務名稱 | | --cron | Cron 運算式,"0 9 * * *" 表示每天 9:00 執行 | | --tz | 時區,設為 "UTC" 即國際標準時間,可按需替換為您所在時區(如 "America/New_York"、"Europe/London") | | --message | 發送給 Agent 的提示詞,告訴 AI 要抓取什麼內容、如何總結 | | --channel | 推送渠道。Cron 定時任務支援 discord 和 telegram,此處設為 discord。 | | --announce | 將結果推送到已配置的 Discord 頻道中。 |
建立成功後將返回 JSON 格式的任務資訊,包含任務 ID 和下次執行時間。 2. 建立任務後,可以立即手動觸發一次以驗證效果。
- 查看工作清單,擷取任務 ID。
openclaw cron list
- 手動觸發執行。
openclaw cron run <task_ID> --timeout 120000
- 查看執行結果。
openclaw cron runs --id <task_ID>
當輸出中 "status": "ok" 且 "delivered": true 時,表示新聞已成功推送到 Discord。
案例四:股市監控與分析
讓 OpenClaw 分析股票走勢,並提供技術面分析和投資建議。
說明
AI 產生內容僅供參考,不構成實際的投資建議或決策依據。配置步驟
-
安裝 Skill
在 OpenClaw 對話中輸入以下指令,OpenClaw 會自動完成安裝:
Install the manus-stock-analysis skill
- 安裝完成後,返回終端並重啟網關使 Skill 生效。
openclaw gateway restart
驗證 Skill 是否安裝成功。
openclaw skills list
- 在 OpenClaw 對話中輸入股市相關問題,例如
Analyze NVDA stock。
瞭解更多
Skill
Skill 是可擴充的能力模組,Agent 會根據請求自動匹配並載入對應的 Skill。OpenClaw 支援查看和啟用內建 Skill,從 ClawHub安裝社區 Skill,或建立自訂 Skill。
查看已有 Skill
- 執行以下命令查看已安裝的 Skill 及其狀態。
# 列出已安裝的 Skill
openclaw skills list
# 查看 Skill 狀態(已啟用、已禁用、缺少依賴等)
openclaw skills check
# 查看特定 Skill 的詳細資料
openclaw skills info <skill-name>
- 內建 Skill 預設未啟用,需在
~/.openclaw/openclaw.json中通過skills.allowBundled白名單啟用,只有列在其中的內建 Skill 才會被載入。
{
"skills": {
"allowBundled": [
"github",
"weather",
"summarize",
"coding-agent",
"clawhub",
"nano-pdf",
"google-web-search",
"image-lab"
]
}
}
部分內建 Skill需要配置對應的第三方 API Key 才能使用,請在 ~/.openclaw/openclaw.json 的 skills.entries 中配置,具體請參考 Skills 配置文檔。
尋找更多 Skill
可以通過以下兩種方式尋找並安裝更多 Skill。
-
通過 ClawHub 搜尋安裝
ClawHub 提供 3,000+ 個社區 Skill,可以在網站上瀏覽,也可以通過命令列搜尋。
# 按關鍵詞搜尋
npx clawhub search [關鍵詞]
# 瀏覽最新動向的 Skill
npx clawhub explore
找到合適的 Skill 後,執行以下命令安裝,安裝完成後重啟網關即可使用。
npx clawhub install <skill-name>
-
直接在 OpenClaw 中提問
在對話中直接描述需求,例如
幫我找一個可以查天氣的 Skill,OpenClaw 會自動搜尋並安裝。
建立自訂 Skill
- 建立 Skill 目錄。
mkdir -p ~/.openclaw/workspace/skills/my-custom-skill
- 在該目錄下建立
SKILL.md檔案。檔案由 YAML 前置中繼資料和 Markdown 指令兩部分組成,其中name和description為必要欄位。Agent 根據description判斷是否載入該 Skill,請確保描述準確。
---
name: my-custom-skill
description: 簡短描述
---
# My Custom Skill
當使用者請求 XXX 時,執行以下操作:
1. 使用 bash 工具運行 xxx 命令
2. 解析輸出結果
3. 以表格形式返回給使用者
- 重啟網關使 Skill 生效。
# 重啟網關
openclaw gateway restart
# 查看 Skill 是否生效
openclaw skills list
更多 Skill 配置說明請參考OpenClaw 官方文檔。
常見問題
如何查看已配置的模型?
在終端輸入openclaw tui,進入 OpenClaw 終端命令列,接著輸入/model查看模型列表。按斷行符號鍵選中模型,按Esc鍵退出模型列表。
為什麼報錯"HTTP 401: Incorrect API key provided."、"No API key found for provider xxx"或"HTTP 401: invalid_iam_token"?
可能原因:
- API Key 無效、到期、為空白、格式錯誤,或與端點環境不匹配。請檢查 API Key 是否與所使用的付費方式匹配,並確保複製完整且無空格;確認訂閱狀態有效。
- OpenClaw 的歷史配置緩衝導致配置錯誤,請刪除
~/.openclaw/agents/main/agent/models.json檔案中的providers配置項,並重啟 OpenClaw。 invalid_iam_token表示 API Key 經 IAM 鑒權校正失敗。常見情境:API Key 已被吊銷或禁用、API Key 歸屬的地區與 Base URL 所指地區不一致(例如 API Key 在華北2(北京),但 Base URL 指向新加坡)、使用 STS 臨時憑證且已到期。請核對 API Key 與 Base URL 歸屬同一地區,並確認 API Key 狀態正常。
我已經配置過DingTalk等其他渠道,如何安全地添加新套餐模型(防止原有配置丟失)?
-
請勿直接全量覆蓋。直接"全部替換"會覆蓋掉自訂配置,請進行局部修改。
-
可以選擇以下方式完成配置:
- 若 OpenClaw 可正常對話:直接在 OpenClaw 對話中輸入指令完成配置合并。
- 若 OpenClaw 未配置模型或無法對話:請手動編輯
~/.openclaw/openclaw.json,只修改需要變更的欄位,保留原有配置不變。
重啟網關後,已有會話可能無法正常對話,請重啟會話。
報錯 device identity required 怎麼辦?
詳細報錯資訊:
http://127.0.0.1:18791/15:05:56 [ws] closed before connect conn=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx remote=127.0.0.1 fwd=n/a origin=n/a host=127.0.0.1:18789 ua=n/a code=1008 reason=device identity required
原因:用戶端串連網關時未提供裝置身份資訊,通常由以下原因導致:
- 首次開啟瀏覽器訪問地址,尚未完成裝置配對。
- 瀏覽器緩衝被清除,裝置密鑰丟失。
- 重裝或升級 OpenClaw 後,
~/.openclaw/identity/目錄下的密鑰檔案缺失。
在終端執行以下命令,允許當前裝置串連並重建瀏覽器訪問地址:
openclaw devices approve --latest
openclaw dashboard --no-open
如果仍未解決,先清除異常的裝置記錄再重試:
openclaw devices clear --pending --yes
openclaw dashboard --no-open
執行 openclaw devices list,確認裝置顯示在 Paired 列表中即為正常。
沒有主動使用 OpenClaw,但仍產生了 Token 消耗
原因:OpenClaw 內建心跳機制(Heartbeat),網關運行期間會按固定間隔(預設 30 分鐘)自動調用已配置的模型,檢查是否有待處理任務。每次心跳都會消耗少量 Token。
如何確認:查看 ~/.openclaw/agents/main/sessions/ 目錄下的會話記錄檔案(.jsonl),其中包含 [OpenClaw heartbeat poll] 標記的心跳調用記錄。
- 停止網關:不使用時執行
openclaw gateway stop,心跳隨即停止。 - 增大心跳間隔:在
~/.openclaw/openclaw.json中設定agents.defaults.heartbeat.every,例如"2h"表示每 2 小時一次。