openclaw

Connect LLMs to messaging platforms via a WebSocket gateway for multi-channel agent messaging.

2|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/zot24/skills --skill openclaw-zot24
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw
Source: https://github.com/zot24/skills/tree/main/skills/openclaw/skills/openclaw
Command: npx skills add https://github.com/zot24/skills --skill openclaw-zot24

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenClaw eliminates the friction of connecting large language models to real messaging channels and managing multi-channel agent routing, configuration, and operational workflows.

Core Features & Use Cases

  • Gateway & Routing: Central WebSocket gateway that multiplexes APIs, sessions, and channel connections.
  • Channel Integrations: Supports WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams, Google Chat, Matrix, BlueBubbles, Zalo, Mattermost, Twitch and more for sending and receiving messages.
  • Workspace & Skills: Workspace-based skill system with persistent sessions, memory, CLI tooling, MCP support, and AgentSkills-compatible skill packaging.
  • Use Case: Deploy a gateway that receives WhatsApp messages, runs an agent using an Anthropic/OpenAI model to generate a reply, and delivers responses back to the originating channel while preserving session context and logs.

Quick Start

Start the OpenClaw gateway, configure an API key and link a messaging channel, then send an agent message through the gateway.

Frequently Asked Questions about openclaw

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I connect an LLM to WhatsApp and Telegram for automated messaging?

You can connect an LLM to multiple messaging platforms by deploying this WebSocket gateway to multiplex API sessions and channel connections, enabling automated message delivery and agent-run replies across WhatsApp and Telegram.

What is the best way to route multi-channel agent messages from different platforms?

The best way to route multi-channel agent messages is using a central WebSocket gateway that multiplexes sessions and channel connections, ensuring deterministic routing and tool invocation for messages received from platforms like Slack, Discord, and Microsoft Teams.

Can I use Anthropic and OpenAI models with a custom messaging gateway?

Yes, you can use Anthropic and OpenAI models by configuring the provider and model settings within the gateway, allowing the system to run agents that generate replies and deliver them back to the originating messaging channel.

Does the multi-channel messaging gateway support persistent session memory?

Yes, the multi-channel messaging gateway supports persistent session memory and workspace-based skill systems, allowing agents to maintain context across interactions and utilize AgentSkills-compatible packaging for tool invocation.

How do I start sending agent messages through a WebSocket gateway?

To start sending agent messages through a WebSocket gateway, launch the server, configure your model provider's API key, link a messaging channel via CLI commands, and then route messages through the established connection.

What messaging platforms can I integrate with an LLM agent gateway?

You can integrate an LLM agent gateway with WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams, Google Chat, Matrix, BlueBubbles, Zalo, Mattermost, and Twitch for sending and receiving automated messages.