OpenClaw Introduction OpenClaw 是一款開源的個人 AI 數位助理，讓你在各種通訊平台上擁有專屬的智慧管家。無論是自動回覆訊息、整理資訊、串接工作流程，OpenClaw 都能幫你搞定。 中文手冊： OpenClaw：在 WhatsApp 與 Telegram 輕鬆使用你的 AI Agent | OpenClaw 李宏毅:  解剖小龍蝦 — 以 OpenClaw 為例介紹 AI Agent 的運作原理 - YouTube 為什麼我拖了一個多月才開始使用OpenClaw？ （附接入飛書完整詳細教程，新手必看） OpenClaw 教學：26 個 Tools + 53 個 Skills 完整指南 | WenHao Yu OpenClaw：在 WhatsApp 與 Telegram 輕鬆使用你的 AI Agent | OpenClaw OpenClaw 中文教程 - 个人 AI 智能体开发一站式社区 OpenClaw 新手必备！安装实用Skills，模型选择，浏览器自动化等！ – 零度博客 Resources Awesome OpenClaw Agents ClawHub OpenClaw CLI 建議模型列表 各種專家級 AI 助理 193 個即插即用的 AI 專家角色 Installation 【保姆级】OpenClaw 全网最细教学：安装→Skills实战→多Agent协作，1 小时全精通！ | 小林的博客-AI学长 YT: 【保姆级】OpenClaw 全网最细教学：安装→Skills实战→多Agent协作，1 小时全精通！ - YouTube With Docker OpenClaw Docker 部署完全指南：从零搭建你的私有 AI Agent Self-hosting OpenClaw with Docker and Tailscale on a $5 VPS Docker 部署 OpenClaw：从踩坑到跑通的完整记录 | Yuxu Ge git clone https://github.com/openclaw/openclaw cd openclaw export OPENCLAW_IMAGE="ghcr.io/openclaw/openclaw:latest" ./scripts/docker/setup.sh Debian 13 Run as root # Install Node.js # Run as root curl -fsSL https://deb.nodesource.com/setup_24.x | bash - apt install nodejs Run as non-root # Switch to non-root account # NOTE: Node.js 22.14 or newer is required for openclaw su - node -v npm --version mkdir -p "$HOME/.npm-global" npm config set prefix "$HOME/.npm-global" npm prefix -g export PATH="$HOME/.npm-global/bin:$PATH" Edit: ~/.bashrc export PATH="$HOME/.npm-global/bin:$PATH" Install openclaw npm install -g openclaw@latest openclaw onboard --install-daemon Post-Install 訂製 AI 助理 使用 3 個檔案量身訂製助理 SOUL.md — 身份、記憶、溝通風格、關鍵規則 AGENTS.md — 核心使命、技術交付物、工作流程 IDENTITY.md — 名稱與簡介 Timezone openclaw config set agents.defaults.userTimezone "Asia/Taipei" CLI Commands Check Service docker compose run --rm openclaw-cli status docker compose run --rm openclaw-cli gateway status Pairing required Approve the device docker compose run --rm openclaw-cli devices list docker compose run --rm openclaw-cli devices approve Model Configuration # 主要模型設置 openclaw models list openclaw models status openclaw models set openclaw models set-image # 備用模型設置 openclaw models fallbacks list openclaw models fallbacks add openclaw models fallbacks remove openclaw models fallbacks clear Telegram Configuration Create a Bot from Telegram Open Telegram Chat with @BotFather   Run /newbot , follow prompts to create your bot, and save the token. Bot Name: Bot Username:   Go to OpenClaw CLI docker compose run --rm openclaw-cli channels add --channel telegram --token "" Go to Telegram Open you-bot Send "Hi" Getting a pairing code "XXXXX" Go to OpenClaw CLI docker compose run --rm openclaw-cli pairing list telegram docker compose run --rm openclaw-cli pairing approve telegram XXXXX Done Bot Commands /btw : 題外話，在不打斷目前對話（主任務），可以臨時問一個小問題，其內容不會進入主對話的上下文。 /subagent : 子代理，在不打斷目前對話（主任務），呼叫另一個代理執行其他任務，其任務結果會納入主任務的上下文。 /new : 新對話，建立新的對話（任務），全新的上下文，可節省 Token 用量。 Gateway Local only (default) 遠端存取可以使用 SSH Port Forwarding ~/.openclaw/openclaw.json : "gateway": { "port": 18789, "mode": "local", "bind": "loopback", "controlUi": { "allowedOrigins": [ "http://localhost:18789", "http://127.0.0.1:18789" ] }, "auth": { "mode": "token", "token": "YOUR-OPENCLAW-TOKEN" }, Tailscale openclaw.json 的 tailscale 功能不適用在 Docker 環境。 Tailscale Console: Enable HTTPS Certicficates OpenClaw Host: Run sudo tailscale serve --bg --https=443 127.0.0.1:18789   tailscale serve status   Change ~/.openclaw/openclaw.json as follows Connect to tailnet, and then visit https://your-openclaw-device.tailnet-domain/?token=YOUR-TOKEN ,  such as https://dockers-vm.tailcb58c9.ts.net/ ?token=YOUR-TOKEN ~/.openclaw/openclaw.json : mode: local bind: loopback trustedProxies: ["127.0.0.1", "::1"] allowedOrigins: https://yourdevice.tailnet-domain "gateway": { "port": 18789, "mode": "local", "bind": "loopback", "trustedProxies": ["127.0.0.1", "::1"], "controlUi": { "allowedOrigins": [ "http://localhost:18789", "http://127.0.0.1:18789", "https://yourdevice.tailnet-domain" ] }, "auth": { "mode": "token", "token": "YOUR-OPENCLAW-TOKEN" }, openclaw.json 的 tailscale 模式比較（不適用在 Docker 環境） 模式 存取範圍 HTTPS 認證 適用場景 serve 限 tailnet 自動 Tailscale identity headers/Token/Password 個人使用 funnel 公眾網路 自動 Password Webhook bind: "tailnet" 限 tailnet 無 Token/Password 低延遲 off 限 localhost 無 Token SSH Port Forward Skill 3rd Party Architecture Diagram Generator : 繪製架構圖並輸出 HTML 格式。 Khazix Skills : 橫縱分析法深度研究。 FAQ Context limit exceeded Context limit exceeded. I've reset our conversation to start fresh - please try again. To prevent this, increase your compaction buffer by setting agents.defaults.compaction.reserveTokensFloor to 20000 or higher in your config. Cause: 目前使用模型的 Context Window 與 壓縮緩衝參數不匹配。 Solution: 以 Gemma4-31B-it 為例 Edit: ~/.openclaw/openclaw.json contextWindow : 128000 reserveTokensFloor : 40000 "models": { "mode": "merge", "providers": { "custom-cpamc": { "baseUrl": "http://192.168.31.89:8317/v1", "api": "openai-completions", "apiKey": "sk-cvgaT1Z3EhJRBB5pu", "models": [ { "id": "gemma-4-31b-it", "name": "gemma-4-31b-it (Custom Provider)", "contextWindow": 128000, "maxTokens": 4096, "input": [ "text" ], "agents": { "defaults": { "workspace": "/home/alang/.openclaw/workspace", "model": { "primary": "custom-cpamc/gemma-4-31b-it" }, "models": { "custom-cpamc/gemma-4-31b-it": {} }, "compaction": { "reserveTokensFloor": 40000 } } }, 或者使用 CLI openclaw config set agents.defaults.compaction.reserveTokensFloor 40000 LLM idle timeout The model did not produce a response before the LLM idle timeout. Please try again, or increase agents.defaults.llm.idleTimeoutSeconds in your config (set to 0 to disable). Solution: openclaw config set agents.defaults.timeoutSeconds 600 openclaw config set agents.defaults.llm.idleTimeoutSeconds 600 gateway connect failed gateway connect failed: GatewayClientRequestError: pairing required 檢查有無 pending devices openclaw devices list openclaw devices list --json