🦞 OpenClaw — Personal AI Assistant (Tianjun Fork)

本 Fork 针对任何本地小参数模型进行优化，不限特定硬件。只要在 openclaw.json 中配置 local provider（支持 Ollama、vLLM、llama.cpp 等任何 OpenAI 兼容 API），即可自动启用所有优化。已在后摩智能 M50 NPU + Qwen3 30B / GPT-OSS 20B 上验证通过。

Fork 改动

1. 本地模型提示词优化 — 精简 system prompt，首字响应时间从 25-40 秒降到约 350 毫秒
2. 工具精简 — 只保留 19 个常用工具，裁剪参数和描述，减少输入 token 数量
3. 实时搜索能力 — 本地模型自动检测实时问题并搜索（Google Serper 优先，DuckDuckGo 备用），搜索结果注入对话防止模型编造答案；云端模型无搜索密钥时隐藏搜索工具避免报错
4. 网络安全调整 — 放行内网测试地址，拦截云元数据地址

适用范围

• 推理后端: Ollama、vLLM、llama.cpp、SGLang 等任何兼容 OpenAI API 的服务
• 硬件: NPU、GPU、CPU 均可，不绑定特定硬件
• 模型: 7B-30B 参数范围的小模型效果最佳（如 Qwen3、Llama、Mistral、GPT-OSS 等）
• 触发方式: 在 openclaw.json 中将推理后端配置为 local provider，优化自动生效

---

This fork optimises OpenClaw for any local small-parameter model, regardless of hardware. Simply configure a local provider in openclaw.json (works with Ollama, vLLM, llama.cpp, or any OpenAI-compatible API) and all optimisations activate automatically. Validated on the Houmo M50 NPU with Qwen3 30B and GPT-OSS 20B.

Changelog

1. Prompt optimisation — Slimmed system prompt, TTFT reduced from 25–40s to ~350ms
2. Tool slimming — Whitelisted 19 essential tools with trimmed parameters and descriptions to cut token usage
3. Real-time search — Auto-detects real-time queries for local models and searches via Google Serper (with DuckDuckGo fallback), injecting results into the conversation to prevent hallucination; hides the search tool from cloud models when no API key is present
4. Network security — Permits RFC 2544 test addresses, blocks cloud metadata endpoints

Compatibility

• Inference backends: Ollama, vLLM, llama.cpp, SGLang, or any OpenAI-compatible API
• Hardware: NPU, GPU, or CPU — not tied to any specific hardware
• Models: Best suited for 7B–30B parameter models (e.g. Qwen3, Llama, Mistral, GPT-OSS)
• Activation: Configure your inference backend as a local provider in openclaw.json — optimisations apply automatically

---

安装 (中文)

注意: 本 Fork 不发布到 npm，不能用 npm install -g openclaw 安装。请从源码构建。

前置要求

• Node.js ≥ 22
• pnpm (npm install -g pnpm)
• git（离线安装可不需要）

方式一：一键安装脚本（Deepin/Debian 系 Linux）

适用于全新机器，自动安装所有依赖（nvm、Node.js、pnpm、git）并构建。脚本会自动检测同目录下的源码压缩包（.tar.gz 或 .zip），优先使用本地包跳过 git clone。

# 克隆或下载本仓库
git clone --depth 1 https://github.com/DexterSLamb/openclaw-tianjun.git
cd openclaw-tianjun

# 可选：如果网络慢，先在浏览器下载源码包放到当前目录
# 浏览器打开: https://github.com/DexterSLamb/openclaw-tianjun/archive/refs/heads/main.zip
# 或: https://github.com/DexterSLamb/openclaw-tianjun/archive/refs/heads/main.tar.gz

# 运行安装脚本
chmod +x scripts/install-openclaw-fork.sh
./scripts/install-openclaw-fork.sh

方式二：手动从源码构建

git clone https://github.com/DexterSLamb/openclaw-tianjun.git
cd openclaw-tianjun
pnpm install
node scripts/tsdown-build.mjs
pnpm ui:build

# 启动引导
node openclaw.mjs onboard --install-daemon

方式三：离线安装（无需 git）

网络较慢或无法访问 GitHub 时，可在其他机器下载后离线安装：

1. 在能访问 GitHub 的机器上下载：https://github.com/DexterSLamb/openclaw-tianjun/archive/refs/heads/main.zip
2. 将 zip 文件拷贝到目标机器，解压并构建：

unzip openclaw-tianjun-main.zip
cd openclaw-tianjun-main
pnpm install
node scripts/tsdown-build.mjs
pnpm ui:build
node openclaw.mjs onboard --install-daemon

NPU 本地模型部署（后摩智能 M50）

如果使用后摩智能 M50 NPU 运行本地模型，还需要：

1. 安装 NPU 驱动和 SDK（参见后摩智能文档）
2. 安装 llama-server：

# 需要 HLIELLama 安装包（向后摩智能获取）
./install-llama-server-1.4.0.sh

3. 在 ~/.openclaw/openclaw.json 中添加 local provider：

{
  "models": {
    "providers": {
      "local": {
        "baseUrl": "http://127.0.0.1:17701/v1",
        "apiKey": "no-key",
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3-30b",
            "name": "Qwen3 30B (NPU)",
            "reasoning": false,
            "input": ["text"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 32768,
            "maxTokens": 8192
          },
          {
            "id": "gpt-oss-20b",
            "name": "GPT-OSS 20B (NPU)",
            "reasoning": false,
            "input": ["text"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 65536,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": { "defaults": { "model": "local/qwen3-30b" } },
  "gateway": {
    "port": 18789,
    "mode": "local",
    "bind": "loopback",
    "auth": { "mode": "token", "token": "openclaw-local-token" }
  }
}

---

Installation (English)

Note: This fork is NOT published to npm. Do not use npm install -g openclaw. Build from source instead.

Prerequisites

• Node.js ≥ 22
• pnpm (npm install -g pnpm)
• git (not required for offline install)

Option 1: One-click install script (Deepin/Debian-based Linux)

For fresh machines — automatically installs all dependencies (nvm, Node.js, pnpm, git) and builds. The script auto-detects local source archives (.tar.gz or .zip) in the same directory and uses them instead of git clone.

git clone --depth 1 https://github.com/DexterSLamb/openclaw-tianjun.git
cd openclaw-tianjun

# Optional: download source archive first if network is slow
# https://github.com/DexterSLamb/openclaw-tianjun/archive/refs/heads/main.zip

chmod +x scripts/install-openclaw-fork.sh
./scripts/install-openclaw-fork.sh

Option 2: Manual build from source

git clone https://github.com/DexterSLamb/openclaw-tianjun.git
cd openclaw-tianjun
pnpm install
node scripts/tsdown-build.mjs
pnpm ui:build

# Launch onboarding
node openclaw.mjs onboard --install-daemon

Option 3: Offline install (no git required)

If GitHub access is slow or unavailable, download the zip on another machine and transfer it:

1. Download: https://github.com/DexterSLamb/openclaw-tianjun/archive/refs/heads/main.zip
2. Unzip and build:

unzip openclaw-tianjun-main.zip
cd openclaw-tianjun-main
pnpm install
node scripts/tsdown-build.mjs
pnpm ui:build
node openclaw.mjs onboard --install-daemon

NPU local model deployment (Houmo M50)

To run local models on a Houmo M50 NPU:

1. Install NPU drivers and SDK (see Houmo documentation)
2. Install llama-server:

# Requires HLIELLama package (obtain from Houmo)
./install-llama-server-1.4.0.sh

3. Add a local provider to ~/.openclaw/openclaw.json:

{
  "models": {
    "providers": {
      "local": {
        "baseUrl": "http://127.0.0.1:17701/v1",
        "apiKey": "no-key",
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3-30b",
            "name": "Qwen3 30B (NPU)",
            "reasoning": false,
            "input": ["text"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 32768,
            "maxTokens": 8192
          },
          {
            "id": "gpt-oss-20b",
            "name": "GPT-OSS 20B (NPU)",
            "reasoning": false,
            "input": ["text"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 65536,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": { "defaults": { "model": "local/qwen3-30b" } },
  "gateway": {
    "port": 18789,
    "mode": "local",
    "bind": "loopback",
    "auth": { "mode": "token", "token": "openclaw-local-token" }
  }
}

---

EXFOLIATE! EXFOLIATE!

OpenClaw is a personal AI assistant you run on your own devices. It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WebChat). It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.

If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.

Website · Docs · Vision · DeepWiki · Getting Started · Updating · Showcase · FAQ · Wizard · Nix · Docker · Discord

Preferred setup: run the onboarding wizard (openclaw onboard) in your terminal. The wizard guides you step by step through setting up the gateway, workspace, channels, and skills. The CLI wizard is the recommended path and works on macOS, Linux, and Windows (via WSL2; strongly recommended). Works with npm, pnpm, or bun. New install? Start here: Getting started

Sponsors

OpenAI	Vercel	Blacksmith	Convex

Subscriptions (OAuth):

• OpenAI (ChatGPT/Codex)

Model note: while many providers/models are supported, for the best experience and lower prompt-injection risk use the strongest latest-generation model available to you. See Onboarding.

Models (selection + auth)

• Models config + CLI: Models
• Auth profile rotation (OAuth vs API keys) + fallbacks: Model failover

Install (recommended)

Runtime: Node ≥22.

npm install -g openclaw@latest
# or: pnpm add -g openclaw@latest

openclaw onboard --install-daemon

The wizard installs the Gateway daemon (launchd/systemd user service) so it stays running.

Quick start (TL;DR)

Runtime: Node ≥22.

Full beginner guide (auth, pairing, channels): Getting started

openclaw onboard --install-daemon

openclaw gateway --port 18789 --verbose

# Send a message
openclaw message send --to +1234567890 --message "Hello from OpenClaw"

# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/BlueBubbles/IRC/Microsoft Teams/Matrix/Feishu/LINE/Mattermost/Nextcloud Talk/Nostr/Synology Chat/Tlon/Twitch/Zalo/Zalo Personal/WebChat)
openclaw agent --message "Ship checklist" --thinking high

Upgrading? Updating guide (and run openclaw doctor).

Development channels

• stable: tagged releases (vYYYY.M.D or vYYYY.M.D-<patch>), npm dist-tag latest.
• beta: prerelease tags (vYYYY.M.D-beta.N), npm dist-tag beta (macOS app may be missing).
• dev: moving head of main, npm dist-tag dev (when published).

Switch channels (git + npm): openclaw update --channel stable|beta|dev. Details: Development channels.

From source (development)

Prefer pnpm for builds from source. Bun is optional for running TypeScript directly.

git clone https://github.com/openclaw/openclaw.git
cd openclaw

pnpm install
pnpm ui:build # auto-installs UI deps on first run
pnpm build

pnpm openclaw onboard --install-daemon

# Dev loop (auto-reload on TS changes)
pnpm gateway:watch

Note: pnpm openclaw ... runs TypeScript directly (via tsx). pnpm build produces dist/ for running via Node / the packaged openclaw binary.

Security defaults (DM access)

OpenClaw connects to real messaging surfaces. Treat inbound DMs as untrusted input.

Full security guide: Security

Default behavior on Telegram/WhatsApp/Signal/iMessage/Microsoft Teams/Discord/Google Chat/Slack:

• DM pairing (dmPolicy="pairing" / channels.discord.dmPolicy="pairing" / channels.slack.dmPolicy="pairing"; legacy: channels.discord.dm.policy, channels.slack.dm.policy): unknown senders receive a short pairing code and the bot does not process their message.
• Approve with: openclaw pairing approve <channel> <code> (then the sender is added to a local allowlist store).
• Public inbound DMs require an explicit opt-in: set dmPolicy="open" and include "*" in the channel allowlist (allowFrom / channels.discord.allowFrom / channels.slack.allowFrom; legacy: channels.discord.dm.allowFrom, channels.slack.dm.allowFrom).

Run openclaw doctor to surface risky/misconfigured DM policies.

Highlights

• Local-first Gateway — single control plane for sessions, channels, tools, and events.
• Multi-channel inbox — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, BlueBubbles (iMessage), iMessage (legacy), IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WebChat, macOS, iOS/Android.
• Multi-agent routing — route inbound channels/accounts/peers to isolated agents (workspaces + per-agent sessions).
• Voice Wake + Talk Mode — wake words on macOS/iOS and continuous voice on Android (ElevenLabs + system TTS fallback).
• Live Canvas — agent-driven visual workspace with A2UI.
• First-class tools — browser, canvas, nodes, cron, sessions, and Discord/Slack actions.
• Companion apps — macOS menu bar app + iOS/Android nodes.
• Onboarding + skills — wizard-driven setup with bundled/managed/workspace skills.

Star History

Everything we built so far

Core platform

• Gateway WS control plane with sessions, presence, config, cron, webhooks, Control UI, and Canvas host.
• CLI surface: gateway, agent, send, wizard, and doctor.
• Pi agent runtime in RPC mode with tool streaming and block streaming.
• Session model: main for direct chats, group isolation, activation modes, queue modes, reply-back. Group rules: Groups.
• Media pipeline: images/audio/video, transcription hooks, size caps, temp file lifecycle. Audio details: Audio.

Channels

• Channels: WhatsApp (Baileys), Telegram (grammY), Slack (Bolt), Discord (discord.js), Google Chat (Chat API), Signal (signal-cli), BlueBubbles (iMessage, recommended), iMessage (legacy imsg), IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WebChat.
• Group routing: mention gating, reply tags, per-channel chunking and routing. Channel rules: Channels.

Apps + nodes

• macOS app: menu bar control plane, Voice Wake/PTT, Talk Mode overlay, WebChat, debug tools, remote gateway control.
• iOS node: Canvas, Voice Wake, Talk Mode, camera, screen recording, Bonjour + device pairing.
• Android node: Connect tab (setup code/manual), chat sessions, voice tab, Canvas, camera/screen recording, and Android device commands (notifications/location/SMS/photos/contacts/calendar/motion/app update).
• macOS node mode: system.run/notify + canvas/camera exposure.

Tools + automation

• Browser control: dedicated openclaw Chrome/Chromium, snapshots, actions, uploads, profiles.
• Canvas: A2UI push/reset, eval, snapshot.
• Nodes: camera snap/clip, screen record, location.get, notifications.
• Cron + wakeups; webhooks; Gmail Pub/Sub.
• Skills platform: bundled, managed, and workspace skills with install gating + UI.

Runtime + safety

• Channel routing, retry policy, and streaming/chunking.
• Presence, typing indicators, and usage tracking.
• Models, model failover, and session pruning.
• Security and troubleshooting.

Ops + packaging

• Control UI + WebChat served directly from the Gateway.
• Tailscale Serve/Funnel or SSH tunnels with token/password auth.
• Nix mode for declarative config; Docker-based installs.
• Doctor migrations, logging.

How it works (short)

WhatsApp / Telegram / Slack / Discord / Google Chat / Signal / iMessage / BlueBubbles / IRC / Microsoft Teams / Matrix / Feishu / LINE / Mattermost / Nextcloud Talk / Nostr / Synology Chat / Tlon / Twitch / Zalo / Zalo Personal / WebChat
               │
               ▼
┌───────────────────────────────┐
│            Gateway            │
│       (control plane)         │
│     ws://127.0.0.1:18789      │
└──────────────┬────────────────┘
               │
               ├─ Pi agent (RPC)
               ├─ CLI (openclaw …)
               ├─ WebChat UI
               ├─ macOS app
               └─ iOS / Android nodes

Key subsystems

• Gateway WebSocket network — single WS control plane for clients, tools, and events (plus ops: Gateway runbook).
• Tailscale exposure — Serve/Funnel for the Gateway dashboard + WS (remote access: Remote).
• Browser control — openclaw‑managed Chrome/Chromium with CDP control.
• Canvas + A2UI — agent‑driven visual workspace (A2UI host: Canvas/A2UI).
• Voice Wake + Talk Mode — wake words on macOS/iOS plus continuous voice on Android.
• Nodes — Canvas, camera snap/clip, screen record, location.get, notifications, plus macOS‑only system.run/system.notify.

Tailscale access (Gateway dashboard)

OpenClaw can auto-configure Tailscale Serve (tailnet-only) or Funnel (public) while the Gateway stays bound to loopback. Configure gateway.tailscale.mode:

• off: no Tailscale automation (default).
• serve: tailnet-only HTTPS via tailscale serve (uses Tailscale identity headers by default).
• funnel: public HTTPS via tailscale funnel (requires shared password auth).

Notes:

• gateway.bind must stay loopback when Serve/Funnel is enabled (OpenClaw enforces this).
• Serve can be forced to require a password by setting gateway.auth.mode: "password" or gateway.auth.allowTailscale: false.
• Funnel refuses to start unless gateway.auth.mode: "password" is set.
• Optional: gateway.tailscale.resetOnExit to undo Serve/Funnel on shutdown.

Details: Tailscale guide · Web surfaces

Remote Gateway (Linux is great)

It’s perfectly fine to run the Gateway on a small Linux instance. Clients (macOS app, CLI, WebChat) can connect over Tailscale Serve/Funnel or SSH tunnels, and you can still pair device nodes (macOS/iOS/Android) to execute device‑local actions when needed.

• Gateway host runs the exec tool and channel connections by default.
• Device nodes run device‑local actions (system.run, camera, screen recording, notifications) via node.invoke. In short: exec runs where the Gateway lives; device actions run where the device lives.

Details: Remote access · Nodes · Security

macOS permissions via the Gateway protocol

The macOS app can run in node mode and advertises its capabilities + permission map over the Gateway WebSocket (node.list / node.describe). Clients can then execute local actions via node.invoke:

• system.run runs a local command and returns stdout/stderr/exit code; set needsScreenRecording: true to require screen-recording permission (otherwise you’ll get PERMISSION_MISSING).
• system.notify posts a user notification and fails if notifications are denied.
• canvas.*, camera.*, screen.record, and location.get are also routed via node.invoke and follow TCC permission status.

Elevated bash (host permissions) is separate from macOS TCC:

• Use /elevated on|off to toggle per‑session elevated access when enabled + allowlisted.
• Gateway persists the per‑session toggle via sessions.patch (WS method) alongside thinkingLevel, verboseLevel, model, sendPolicy, and groupActivation.

Details: Nodes · macOS app · Gateway protocol

Agent to Agent (sessions_* tools)

• Use these to coordinate work across sessions without jumping between chat surfaces.
• sessions_list — discover active sessions (agents) and their metadata.
• sessions_history — fetch transcript logs for a session.
• sessions_send — message another session; optional reply‑back ping‑pong + announce step (REPLY_SKIP, ANNOUNCE_SKIP).

Details: Session tools

Skills registry (ClawHub)

ClawHub is a minimal skill registry. With ClawHub enabled, the agent can search for skills automatically and pull in new ones as needed.

ClawHub

Chat commands

Send these in WhatsApp/Telegram/Slack/Google Chat/Microsoft Teams/WebChat (group commands are owner-only):

• /status — compact session status (model + tokens, cost when available)
• /new or /reset — reset the session
• /compact — compact session context (summary)
• /think <level> — off|minimal|low|medium|high|xhigh (GPT-5.2 + Codex models only)
• /verbose on|off
• /usage off|tokens|full — per-response usage footer
• /restart — restart the gateway (owner-only in groups)
• /activation mention|always — group activation toggle (groups only)

Apps (optional)

The Gateway alone delivers a great experience. All apps are optional and add extra features.

If you plan to build/run companion apps, follow the platform runbooks below.

macOS (OpenClaw.app) (optional)

• Menu bar control for the Gateway and health.
• Voice Wake + push-to-talk overlay.
• WebChat + debug tools.
• Remote gateway control over SSH.

Note: signed builds required for macOS permissions to stick across rebuilds (see docs/mac/permissions.md).

iOS node (optional)

• Pairs as a node over the Gateway WebSocket (device pairing).
• Voice trigger forwarding + Canvas surface.
• Controlled via openclaw nodes ….

Runbook: iOS connect.

Android node (optional)

• Pairs as a WS node via device pairing (openclaw devices ...).
• Exposes Connect/Chat/Voice tabs plus Canvas, Camera, Screen capture, and Android device command families.
• Runbook: Android connect.

Agent workspace + skills

• Workspace root: ~/.openclaw/workspace (configurable via agents.defaults.workspace).
• Injected prompt files: AGENTS.md, SOUL.md, TOOLS.md.
• Skills: ~/.openclaw/workspace/skills/<skill>/SKILL.md.

Configuration

Minimal ~/.openclaw/openclaw.json (model + defaults):

{
  agent: {
    model: "anthropic/claude-opus-4-6",
  },
}

Full configuration reference (all keys + examples).

Security model (important)

• Default: tools run on the host for the main session, so the agent has full access when it’s just you.
• Group/channel safety: set agents.defaults.sandbox.mode: "non-main" to run non‑main sessions (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
• Sandbox defaults: allowlist bash, process, read, write, edit, sessions_list, sessions_history, sessions_send, sessions_spawn; denylist browser, canvas, nodes, cron, discord, gateway.

Details: Security guide · Docker + sandboxing · Sandbox config

WhatsApp

• Link the device: pnpm openclaw channels login (stores creds in ~/.openclaw/credentials).
• Allowlist who can talk to the assistant via channels.whatsapp.allowFrom.
• If channels.whatsapp.groups is set, it becomes a group allowlist; include "*" to allow all.

Telegram

• Set TELEGRAM_BOT_TOKEN or channels.telegram.botToken (env wins).
• Optional: set channels.telegram.groups (with channels.telegram.groups."*".requireMention); when set, it is a group allowlist (include "*" to allow all). Also channels.telegram.allowFrom or channels.telegram.webhookUrl + channels.telegram.webhookSecret as needed.

{
  channels: {
    telegram: {
      botToken: "123456:ABCDEF",
    },
  },
}

Slack

• Set SLACK_BOT_TOKEN + SLACK_APP_TOKEN (or channels.slack.botToken + channels.slack.appToken).

Discord

• Set DISCORD_BOT_TOKEN or channels.discord.token (env wins).
• Optional: set commands.native, commands.text, or commands.useAccessGroups, plus channels.discord.allowFrom, channels.discord.guilds, or channels.discord.mediaMaxMb as needed.

{
  channels: {
    discord: {
      token: "1234abcd",
    },
  },
}

Signal

• Requires signal-cli and a channels.signal config section.

BlueBubbles (iMessage)

• Recommended iMessage integration.
• Configure channels.bluebubbles.serverUrl + channels.bluebubbles.password and a webhook (channels.bluebubbles.webhookPath).
• The BlueBubbles server runs on macOS; the Gateway can run on macOS or elsewhere.

iMessage (legacy)

• Legacy macOS-only integration via imsg (Messages must be signed in).
• If channels.imessage.groups is set, it becomes a group allowlist; include "*" to allow all.

Microsoft Teams

• Configure a Teams app + Bot Framework, then add a msteams config section.
• Allowlist who can talk via msteams.allowFrom; group access via msteams.groupAllowFrom or msteams.groupPolicy: "open".

WebChat

• Uses the Gateway WebSocket; no separate WebChat port/config.

Browser control (optional):

{
  browser: {
    enabled: true,
    color: "#FF4500",
  },
}

Docs

Use these when you’re past the onboarding flow and want the deeper reference.

• Start with the docs index for navigation and “what’s where.”
• Read the architecture overview for the gateway + protocol model.
• Use the full configuration reference when you need every key and example.
• Run the Gateway by the book with the operational runbook.
• Learn how the Control UI/Web surfaces work and how to expose them safely.
• Understand remote access over SSH tunnels or tailnets.
• Follow the onboarding wizard flow for a guided setup.
• Wire external triggers via the webhook surface.
• Set up Gmail Pub/Sub triggers.
• Learn the macOS menu bar companion details.
• Platform guides: Windows (WSL2), Linux, macOS, iOS, Android
• Debug common failures with the troubleshooting guide.
• Review security guidance before exposing anything.

Advanced docs (discovery + control)

• Discovery + transports
• Bonjour/mDNS
• Gateway pairing
• Remote gateway README
• Control UI
• Dashboard

Operations & troubleshooting

• Health checks
• Gateway lock
• Background process
• Browser troubleshooting (Linux)
• Logging

Deep dives

• Agent loop
• Presence
• TypeBox schemas
• RPC adapters
• Queue

Workspace & skills

• Skills config
• Default AGENTS
• Templates: AGENTS
• Templates: BOOTSTRAP
• Templates: IDENTITY
• Templates: SOUL
• Templates: TOOLS
• Templates: USER

Platform internals

• macOS dev setup
• macOS menu bar
• macOS voice wake
• iOS node
• Android node
• Windows (WSL2)
• Linux app

Email hooks (Gmail)

• docs.openclaw.ai/gmail-pubsub

Molty

OpenClaw was built for Molty, a space lobster AI assistant. 🦞 by Peter Steinberger and the community.

• openclaw.ai
• soul.md
• steipete.me
• @openclaw

Community

See CONTRIBUTING.md for guidelines, maintainers, and how to submit PRs. AI/vibe-coded PRs welcome! 🤖

Special thanks to Mario Zechner for his support and for pi-mono. Special thanks to Adam Doppelt for lobster.bot.

Thanks to all clawtributors: