QVerisBot — OpenClaw with QVeris Universal Toolbox

QVerisBot Your professional AI assistant with QVeris Universal Toolbox. OpenClaw reliability + QVeris integrations for real-world workflows. Quick Start · Docs · 500+ Integrations · DeepWiki · Discord

QVerisBot is a production-focused distribution built by the QVeris AI team on top of OpenClaw. It keeps OpenClaw's local-first architecture and adds a QVeris-first product layer for professional workflows.

It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, Microsoft Teams, WebChat), plus extension channels like X, BlueBubbles, Matrix, Zalo, and Zalo Personal. It can speak and listen on macOS/iOS/Android, and render a live Canvas you control.

Why QVerisBot

• Built on OpenClaw, optimized for real deployment: keeps stable gateway/runtime architecture while improving defaults and onboarding.
• QVeris-first tool experience: integrate with 500+ providers and 10,000+ APIs via a single tool-search + tool-execute workflow.
• China-friendly channel strategy: stronger Feishu and regional ecosystem readiness without sacrificing global channel coverage.
• Faster first-run onboarding: CLI/macOS/web wizard now includes QVeris API setup and X channel credentials in guided flow.
• Enhanced long-term memory: two new bundled hooks — context-digest (rolling cross-session summary injected into system prompt) and session-importance (auto-archives important conversations to memory/important/) — extend memory beyond the single session.

OpenClaw vs QVerisBot (quick comparison)

Area	OpenClaw (base platform)	QVerisBot (this repo)
Positioning	Local-first agent gateway + multi-channel runtime	OpenClaw-based distribution focused on professional tool use and faster production onboarding
Tool ecosystem	Built-in tools + extension mechanism	QVeris Universal Toolbox: qveris_discover + qveris_call + qveris_inspect, with auto session-context resolution
Web search default	Commonly configured with Brave/other providers	During onboarding, defaults web_search to QVeris Smart Search when QVeris is enabled
Channel focus	Broad global channels and plugin model	Adds stronger China-facing defaults/integration (especially Feishu), while keeping full OpenClaw channel coverage
First-run onboarding	Wizard-driven baseline setup	Enhanced wizard flow: QVeris API key setup + X channel credential setup integrated into onboarding
Long-term memory	Session-scoped memory + manual memory files	Adds context-digest (cross-session summary → system prompt) and session-importance (auto-archive important conversations)

Quick Start (5 minutes)

System requirements: Node.js 22.12+ (one-liner auto-installs if missing), Python 3.12+ (for skills)

CLI commands: Use qverisbot as the primary command; openclaw is a compatible alias. For example: qverisbot onboard, qverisbot gateway, qverisbot channels status — all work with openclaw as well.

1. npm install (recommended, fastest)

npm i -g @qverisai/qverisbot
qverisbot onboard

After install, run qverisbot onboard — the wizard guides you through model, QVeris, X channel, and more.

2. One-liner (macOS / Linux)

curl -fsSL https://qveris.ai/qverisbot/install.sh | bash

The script detects Node.js and installs it if missing, then runs qverisbot onboard.

3. Windows PowerShell

irm https://qveris.ai/qverisbot/install.ps1 | iex

4. From source (hackable)

git clone https://github.com/QVerisAI/QVerisBot.git
cd QVerisBot
pnpm install
pnpm ui:build   # first run only
pnpm build
pnpm qverisbot onboard --install-daemon

See Source guide.

---

Verify: Start the gateway and test:

# npm install
qverisbot gateway --port 18789 --verbose
qverisbot agent --message "Hello QVerisBot" --thinking high
# 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)
qverisbot agent --message "Ship checklist" --thinking high

# from source
pnpm qverisbot gateway --port 18789 --verbose
pnpm qverisbot agent --message "Hello QVerisBot" --thinking high

The onboarding wizard guides you through: model auth, QVeris API key, web_search (defaults to QVeris Smart Search), X (Twitter) credentials, channels, and skills. For Feishu setup, see Source guide.

QVeris Universal Toolbox — The Core of QVerisBot

🚀 Why QVerisBot?
Stop writing API wrappers.

  

QVeris connects your AI assistant to the world's data and services
Think of it as an "App Store for AI tools"

Subscriptions (OAuth): Anthropic (Claude Pro/Max) · OpenAI (ChatGPT/Codex)

📦 500+ integrations — Finance · Search · Research · Business · Blockchain · AI · Productivity · News · Weather · Travel · Geospatial · Government

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, WeChat, 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 · Onboarding · Nix · Docker · Discord

Preferred setup: run openclaw onboard in your terminal. OpenClaw Onboard guides you step by step through setting up the gateway, workspace, channels, and skills. It is the recommended CLI setup 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

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 + switching)

• Models config + CLI: Models
• Auth profile rotation (OAuth vs API keys) + fallbacks: Model failover
• Natural language model switching: ask the agent to switch models in conversation (e.g. "use kimi", "switch to sonnet") — the switch_model tool handles alias resolution, fuzzy matching, and confirmation when ambiguous. The /model <name> command also works.

Install (recommended)

Runtime: Node 24 (recommended) or Node 22.16+.

Explore all 500+ integrations →

How the agent uses QVeris tools

QVerisBot exposes three QVeris tools to the agent with built-in routing guidance:

Tool	When to use
qveris_discover	Find tools by capability — real-time data APIs (prices, weather, financials), external service capabilities (image gen, OCR, TTS, translation), geo/location APIs. Not for local file ops, software config, or documentation lookups.
qveris_call	Call a tool returned by qveris_discover. Just provide the tool_id — the session layer auto-resolves all backend routing. Pass parameters as JSON using sample_parameters from the discover result as a template.
qveris_inspect	Re-verify a known tool_id without a full discover — use when the agent has already found a tool in this session and wants to confirm availability or refresh its parameter schema.

Zero ID management for the model. After qveris_discover, the integration layer automatically maps each tool_id to its backend session context. The model calls qveris_call(tool_id, params_to_tool) directly — no discovery_id, no search_id to carry around.

The agent follows a routing decision tree before calling qveris_discover:

1. Local operation? (read files, check config, session status) → use local tools, skip QVeris
2. Need a web page or article? → use web_search / web_fetch directly
3. Need structured real-time data or an external service? → qveris_discover("weather forecast API") — describe the capability in English, not the task
4. Already used a QVeris tool this session? → qveris_inspect with the known ID to verify, then qveris_call directly
5. None of the above? → do not call QVeris; use web_search or report the limitation

A session-scoped Tool Rolodex tracks successfully called tools. After a tool is used, it is annotated as previously_used in future discover results and listed under session_known_tools, so the agent reuses verified tools instead of re-discovering from scratch.

Large response handling. When a QVeris tool returns data exceeding the transport limit, the response includes a full_content_file_url link to the full dataset on QVeris-managed storage. The integration layer can optionally auto-download and materialize it to the agent's workspace (autoMaterializeFullContent: true), returning a metadata manifest instead of raw bytes. Security boundaries: HTTPS-only, domain-whitelisted to the configured QVeris region, size-capped, no redirects.

What can you build with QVeris?

Scenario	Tools Used	Workflow
Market Research Analyst	Google Search + Firecrawl + DeepSeek + Notion	Search competitors -> Scrape pricing pages -> Summarize -> Save to Notion
Crypto Price Monitor	Binance + AlphaVantage + Finnhub	Query real-time BTC/ETH prices, analyze market sentiment
Image Search Assistant	Brave Search + SerpApi + Shutterstock	Find images, reverse image search, access stock photos

Get your QVeris API key

1. Create account: qveris.ai → Sign Up
2. Get API key: Dashboard → API Keys → Create New Key
3. Use it: Run qverisbot onboard — the wizard prompts for your key, lets you choose your region (qveris.ai global or qveris.cn for China), and configures QVeris + web_search automatically.

Note

QVeris offers a free tier. For production use, purchase credits at qveris.ai/dashboard.

---

What Else Makes QVerisBot Special

• OpenClaw + QVeris optimization layer — structured tool-routing (decision tree + session rolodex), zero-friction qveris_call (no ID management), optional large-response auto-materialization, and dual-region support (qveris.ai / qveris.cn)
• Feishu Native Support — WebSocket-based deep integration, ideal for Chinese enterprise users
• Improved onboarding across CLI/macOS/web wizard flows — guided QVeris API key setup, auto-default web_search to QVeris Xiaosu Smart Search, and built-in X (Twitter) channel credential onboarding
• Multi-channel inbox — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, Feishu, Microsoft Teams, Matrix, Zalo, WebChat
• Voice Wake + Talk Mode — always-on speech for macOS/iOS/Android
• Live Canvas — agent-driven visual workspace
• LLM Proxy Support — HTTP proxy for API calls in network-restricted environments
• One-command bot migration — export a tuned bot's knowledge, memory, and skills to a portable bundle and import it on any machine or OS without copying credentials

QVeris AI · Docs · DeepWiki · Source Guide · Discord

---

Migrating Your Bot

When you move a tuned bot to a new machine or operating system (for example, from macOS to Linux), a simple directory copy breaks because it carries absolute paths and gateway credentials that only make sense on the source host.

qverisbot migrate solves this by exporting only the portable experience — knowledge, memory, skills, and recent session summaries — while actively stripping secrets and rebuilding system-specific state on the target.

What is exported

Content	Included	Notes
Agent workspace files (AGENTS.md, MEMORY.md, etc.)	✅	Secrets redacted before packing
Managed skills (~/.openclaw/agents/*/skills/)	✅	Redacted
Personal skills (~/.openclaw/skills/)	✅	Redacted
Recent session summaries (last 200)	✅	Previews redacted; included for context/memory
API keys, gateway tokens, provider credentials	❌	Never exported
Session raw transcripts	❌	Summaries only
Machine-specific config (openclaw.json)	❌	Re-generated on target via qverisbot onboard

Export

# Export to an auto-named bundle in the current directory
qverisbot migrate export

# Export to a specific path
qverisbot migrate export --output ~/my-bot-backup.tar.gz

# Export a specific agent only
qverisbot migrate export --agent my-agent-id

# Export without session summaries
qverisbot migrate export --sessions-scope none

# 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/WeChat/WebChat)
openclaw agent --message "Ship checklist" --thinking high

The resulting .tar.gz bundle is self-contained and safe to share or store in version control (no secrets inside).

Import

# Import from a local bundle
qverisbot migrate import ./my-bot-backup.tar.gz

# Import from a remote URL (HTTPS)
qverisbot migrate import https://your-host.example.com/bot-bundle.tar.gz

# Import without resetting existing sessions
qverisbot migrate import ./my-bot-backup.tar.gz --no-reset-sessions

# Dry-run — show what would be placed without touching the filesystem
qverisbot migrate import ./my-bot-backup.tar.gz --dry-run

After import, re-run qverisbot onboard (or qverisbot gateway restart) on the target machine to regenerate gateway credentials and service definitions for the new environment.

Doctor — diagnose migration issues

If a bot behaves unexpectedly after moving hosts, run the migration doctor:

qverisbot migrate doctor

# Check a specific bundle file before importing
qverisbot migrate doctor --bundle ./my-bot-backup.tar.gz

# Output machine-readable JSON for scripting
qverisbot migrate doctor --json

The doctor reports:

• Foreign OS path poison — workspace or session config containing /Users/ on Linux, /home/ on macOS, or Windows paths on a POSIX host.
• Gateway token drift — running gateway token differs from the value in config (causes "token mismatch" errors in Web UI and channels).
• Bundle validation — manifest version compatibility and content integrity before an import.

Recommended cross-OS migration flow

# On the source machine
qverisbot migrate export --output bot-bundle.tar.gz

# Transfer the bundle (scp, rsync, cloud storage, etc.)
scp bot-bundle.tar.gz user@new-host:~/

# On the target machine — set up fresh credentials first
qverisbot onboard

# Then import the tuned experience on top
qverisbot migrate import ~/bot-bundle.tar.gz

# Verify everything is clean
qverisbot migrate doctor

---

Troubleshooting

qverisbot: command not found after npm i -g

Your npm global bin directory is likely not in your shell's PATH.

# 1. Find where npm puts global binaries
npm config get prefix
# e.g. /Users/you/.npm-global  →  bin dir is /Users/you/.npm-global/bin

# 2. Add it to PATH (zsh — macOS default)
echo 'export PATH="$(npm config get prefix)/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc

# 3. Verify
qverisbot --version

Other shells (bash / fish)

bash:

echo 'export PATH="$(npm config get prefix)/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

fish:

echo 'set -gx PATH (npm config get prefix)/bin $PATH' >> ~/.config/fish/config.fish
source ~/.config/fish/config.fish

Alternatively, run without modifying PATH:

# Use npx (always works, no global install needed)
npx @qverisai/qverisbot onboard

# Or use the full path directly
$(npm config get prefix)/bin/qverisbot onboard

---

Reference

System requirements

Component	Minimum	Recommended
Node.js	22.12.0	22.x LTS
pnpm	10.x	10.23.0+
Python	3.12	3.12+ (for skills)

Default behavior on channels

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.dm.allowFrom / channels.slack.dm.allowFrom).

---

OpenClaw upstream reference

QVerisBot is built on OpenClaw. For deep architecture, channel internals, platform operations, and complete config surface, use the upstream docs directly:

• Docs index: https://docs.openclaw.ai
• Architecture: https://docs.openclaw.ai/concepts/architecture
• Gateway runbook: https://docs.openclaw.ai/gateway
• Configuration (all keys): https://docs.openclaw.ai/gateway/configuration
• Channels index: https://docs.openclaw.ai/channels
• Security: https://docs.openclaw.ai/gateway/security
• Web / Control UI: https://docs.openclaw.ai/web
• Remote access: https://docs.openclaw.ai/gateway/remote

Popular deep links

• 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, WeChat, 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.
• Tailscale — secure remote access to your gateway.
• Nodes — iOS/Android/macOS companion apps with voice, canvas, and device commands.
• Browser tool — headless browser automation and web scraping.
• Skills — Python-based extensibility with bundled/managed/workspace skills.
• Troubleshooting — common channel issues and solutions.

QVerisBot-specific docs

• Source setup + Feishu guide: docs/qverisbot-from-source.md
• Bot migration (cross-OS): see Migrating Your Bot above — qverisbot migrate export|import|doctor
• QVeris AI integrations: https://qveris.ai/integrations
• QVeris dashboard / API keys: https://qveris.ai/dashboard
• QVeris tool routing: see How the agent uses QVeris tools above — qveris_discover, qveris_call, qveris_inspect

About QVerisBot

QVerisBot is developed by the QVeris AI team, based on the open-source OpenClaw project (formerly Clawdbot & Moltbot).

• QVeris AI — QVeris Universal Toolbox
• QVerisBot GitHub — Source code
• OpenClaw — Base project
• Documentation — Full documentation

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, onboarding, 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.

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, WeChat (@tencent-weixin/openclaw-weixin), 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 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.
• QVeris Universal Toolbox: search + execute across 500+ providers and 10,000+ APIs — see qveris.ai/integrations.

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 / WeChat / WebChat
               │
               ▼
┌───────────────────────────────┐
│            Gateway            │
│       (control plane)         │
│     ws://127.0.0.1:18789      │
└──────────────┬────────────────┘
               │
               ├─ Pi agent (RPC)
               ├─ CLI (qverisbot / openclaw …)
               ├─ WebChat UI
               ├─ macOS app
               └─ iOS / Android nodes

Chat commands

• 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.

• /status — compact session status (model + tokens, cost when available)

• /model <name> — switch model (alias, partial, or full provider/model; or ask in natural language)

• /new or /reset — reset the session

• /compact — compact session context (summary)

• /think <level> — off|minimal|low|medium|high|xhigh

• /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)

Agent to Agent (sessions_* tools)

• 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)
• /model <name> — switch model (alias, partial, or full provider/model; or ask in natural language)
• /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 macOS Permissions).

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

Channel setup

WhatsApp

• Link the device: qverisbot channels login (stores creds in ~/.openclaw/credentials).
• Allowlist who can talk 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).

{
  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.
• 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).

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".

WeChat

• Official Tencent plugin via @tencent-weixin/openclaw-weixin (iLink Bot API). Private chats only; v2.x requires OpenClaw >=2026.3.22.
• Install: openclaw plugins install "@tencent-weixin/openclaw-weixin", then openclaw channels login --channel openclaw-weixin to scan the QR code.
• Requires the WeChat ClawBot plugin (WeChat > Me > Settings > Plugins); gradual rollout by Tencent.

Feishu

• QVerisBot-native deep integration via WebSocket; ideal for Chinese enterprise users.
• See Feishu setup guide.

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 OpenClaw Onboard 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: