100% Open SourceSelf-HostableCommunity-Driven

OpenClaw was built
for one. ClawScale
is built for everyone.

Connect any AI to WhatsApp, Discord, Telegram, Slack, and 14+ messaging platforms in minutes — not weeks. ClawScale handles multi-tenant isolation, conversation routing, and backend orchestration out of the box. Then share a branded onboarding portal so your users can connect on any channel instantly. No boilerplate. No infrastructure headaches.

Don't want to self-host? Try Palmos AI — our managed automation agent →

ClawScale Architecture
Channels
WhatsApp
Discord
Telegram
Slack
LINE
Teams
Matrix
Signal
WeChat
ClawScale Gateway
AI Backends
OpenClaw #1
OpenClaw #2
GPT-4o
Claude
Custom LLM
Multi-tenant isolation
Many-to-many routing
Per-backend history
The Problem

OpenClaw wasn't built
for a thousand users.

Most teams spend days wiring up webhook handlers, message queues, user-state stores, and AI API calls for each platform — then do it all over again for the next one. And when you need to support hundreds of users, you're stuck building multi-tenancy, conversation isolation, and access control from scratch.

ClawScale does all of this for you — so you can go from zero to live chatbot in minutes.


Core Features

Everything you need to deploy chatbots at scale.

🔗

14+ messaging channels

WhatsApp, Discord, Telegram, Slack, LINE, Teams, Matrix, Signal, WeChat, Instagram, Facebook, and more. Add any channel from the dashboard in seconds — no webhook wiring required.

🤖

Any AI, zero lock-in

Plug in OpenAI, Anthropic, OpenRouter, OpenClaw, or any OpenAI-compatible endpoint. Switch providers or run multiple backends simultaneously — your keys, your choice.

🔄

Many-to-many routing

End-users can talk to multiple agents at once. Messages route to all active backends and replies are labeled by source. Users manage their agent team via slash commands.

🏢

Scale to thousands of users

Every user gets fully isolated conversations, memory, and state. Deploy once and serve hundreds or thousands of users simultaneously — no cross-contamination, no shared context leaking.

🛡️

Dashboard-driven setup

Add channels, configure AI backends, manage users, and monitor conversations — all from a visual dashboard. No config files, no CLI required. Role-based access built in.

🚪

User onboarding portal

Share one link with your users. They see every available channel and connect instantly — scan a QR for WeChat, OAuth into Discord, message a number on WhatsApp. Fully white-label.

How It Works

Three steps to a live chatbot.

01

End-user sends a message

A user messages your bot on WhatsApp, Discord, Telegram, or any connected channel. The channel adapter normalizes the message and posts it to the ClawScale gateway.

02

Gateway routes to backends

ClawScale identifies the user, loads conversation history, parses any commands, and routes the message to the user's active AI backend(s). Multiple backends can respond in parallel.

03

AI responds via the channel

Each backend generates a reply with its own conversation context. Replies are saved, labeled by backend, and delivered back through the original channel. The user sees a natural conversation.

Channels

Deploy across 14+ platforms

Each channel has a dedicated adapter. Paste your credentials in the dashboard, hit Connect, and your chatbot is live. That's it.

WhatsApp (Personal)

QR code scan via Baileys

WhatsApp Business

Meta Cloud API webhook

Discord

Bot token (discord.js)

Telegram

Bot token (grammy long-polling)

Slack

Bot + App-level token (Socket Mode)

LINE

Channel access token + secret (webhook)

Signal

signal-cli REST API

Microsoft Teams

Azure Bot Service (webhook)

Matrix

Homeserver URL + access token

WeChat Work (WeCom)

Bot token (WebSocket)

WeChat Personal

QR code scan (iLink Bot API)

Web Chat Widget

Webhook integration

Onboarding Portal

One link for your users. Every channel, instantly.

You set up the channels. ClawScale generates a branded, user-facing portal your users actually interact with. Share a single URL and they can connect on any platform — no extra frontend work.

How your users connect

💬
DiscordClick an OAuth invite link
📱
WhatsAppSave the number or scan a QR code
💬
WeChatScan a QR code with the app
✈️
TelegramOne-click link opens a chat
💼
SlackInstall link adds the app
🔗
LINE, Signal, Teams...Platform-specific connect link

White-label branding

Customize the portal from the admin dashboard — no code changes.

Custom headline & subtitle
Your own logo
Brand accent color
Hide "Powered by ClawScale"
your-app.com/onboard
🤖
Connect to Acme AI
Choose a platform to start chatting
WhatsApp
Discord
Telegram
AI Backends

Plug in any agent.

ClawScale never injects hidden prompts. Each backend manages its own system prompt, model, and tools. Scale from one OpenClaw instance to many, or mix in other providers.

OpenClaw

Route to one or more OpenClaw instances. OpenClaw manages its own tools, memory, and prompts.

OpenAI

GPT models via OpenAI API. Configure model, system prompt, and API key per backend.

Anthropic

Claude models via Anthropic API. Full system prompt and model control.

OpenRouter

Multi-model aggregator. Access hundreds of models through one API key.

Pulse

Pulse Editor AI agent. Connect to your Pulse instance for coding-aware responses.

Custom

Any OpenAI-compatible endpoint. Self-hosted models, vLLM, Ollama, or any proxy.

P

Palmos AI

A software automation agent that helps SMBs automate customer support, sales workflows, and day-to-day operations — no setup, no infrastructure, no models to configure.

Customer Support

Auto-respond, triage, and escalate across all your channels

Sales Automation

Follow-ups, lead qualification, and CRM updates on autopilot

Operations

Automate repetitive tasks, SOPs, and internal workflows

Get started with Palmos AI →

Hosted at im.palmos.ai — connect to ClawScale in one click

Comparison

OpenClaw vs ClawScale

OpenClaw bundles gateways and agent into one process. ClawScale decouples them so each can scale independently.

FeatureOpenClawClawScale
ArchitectureMonolithicDecoupled gateway + agents
IM channels
Autonomous agentVia OpenClaw backend
User isolationShared memoryPer-user/per-tenant
Scale to 1000s of usersMemory corruption risk
Multiple agent instances
Pluggable AI backends
Many-to-many user/agent
Admin dashboard
Role-based access
Audit logs
User onboarding portalWhite-label, brandable
LicenseOpen sourceOpen source

Both projects are open source. ClawScale uses OpenClaw as one of its pluggable AI backends.

Community

Trusted by teams shipping chatbots worldwide.

ClawScale is MIT-licensed and backed by a growing community of developers deploying IM chatbots at scale. Whether you're adding a channel adapter, fixing a bug, or improving docs — every PR matters.

📦

MIT Licensed

Fork it, modify it, deploy it. No restrictions.

🤝

Open Governance

Roadmap shaped by community discussions and RFCs.

🔧

Easy to Contribute

Clear docs, good-first-issue labels, and fast PR reviews.

🌍

Global Community

Contributors and self-hosters from around the world.

I self-host ClawScale on a $5 VPS and it handles our entire team's WhatsApp and Discord bots. The setup guide had me running in under 10 minutes.

Wei Ling T.
Contributor & self-hoster

I wrote a LINE adapter and submitted a PR. The maintainers reviewed it within a day and it shipped in the next release. Best open-source experience I've had.

Reza A.
Open-source contributor

We run ClawScale on-prem behind our firewall. Full control over our data, no third-party dependencies. Exactly what our compliance team needed.

Joanne C.
DevOps engineer, self-hosting on-prem
Get Started in Minutes

Your chatbots. Every platform. Minutes to deploy.

Clone the repo, run one command, and start deploying AI chatbots to every messaging platform your users are on. No sign-ups. No SaaS fees. No data leaves your server.

terminal
$ git clone https://github.com/ClayPulse/ClawScale
$ cd ClawScale
$ docker compose up
✓ Gateway running on localhost:3000
MIT licensed Self-hostable No vendor lock-in Community-driven Docker ready