openclaw

OpenClaw is a self-hosted personal AI assistant that runs directly on your machine and integrates seamlessly with the messaging apps you already use daily. Unlike cloud-based alternatives, it keeps your conversations private and local while providing instant access across multiple channels.

The platform supports an extensive range of messaging services including WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, WeChat, QQ, and WebChat. This means you can interact with your AI assistant through whichever platform you prefer without switching contexts.

Key capabilities include:

• Multi-agent support with separate workspaces and sessions for different purposes
• Voice interaction with wake-word detection and talk mode on macOS and mobile devices
• Tool automation including browser actions, scheduled cron jobs, and channel-specific actions
• Live Canvas rendering for interactive responses
• Flexible model support with OpenAI integration and fallback options
• Built-in onboarding wizard for guided setup and configuration
• Diagnostic tools via the doctor command for system health checks

The gateway architecture manages sessions, channels, tools, and events while routing messages intelligently to appropriate agents. Installation is straightforward via npm with the recommended openclaw onboard command, which guides you through gateway setup, workspace configuration, and channel pairing. The system runs as a daemon service (launchd on macOS, systemd on Linux) to stay always-on.

Designed for developers and operators who need a capable assistant for both work and personal communications, OpenClaw prioritizes security with DM pairing by default and local-first operation.