OpenClaw Features: Channels, Routing, Media, and UX
Explore OpenClaw's capabilities across channels, routing, media, and user experience. Learn about supported platforms, plugins, multi-agent routing, media handling, and available apps for developers and administrators.
Read this when
- You want a full list of what OpenClaw supports
Highlights
-
Channels, One Gateway covers Discord, iMessage, Signal, Slack, Telegram, WhatsApp, WebChat, and additional platforms.
-
Plugins, A single install command brings in official plugins for Matrix, Nextcloud Talk, Nostr, Twitch, Zalo, and many more.
-
Routing, Isolated sessions enable multi-agent routing.
-
Media, Handles images, audio, video, documents, plus image and video generation.
-
Apps and UI, Includes Windows Hub, browser Control UI, a macOS menu bar app, and mobile nodes.
-
Mobile nodes, iOS and Android nodes offer pairing, voice and chat, plus extensive device commands.
Full list
Channels:
- The core installation ships with Telegram and WebChat; all other channels come as official plugins via
openclaw plugins install @openclaw/<id>(or on demand duringopenclaw onboard/openclaw channels add) - Official plugin channels: Discord, Feishu, Google Chat, iMessage, IRC, LINE, Matrix, Mattermost, Microsoft Teams, Nextcloud Talk, Nostr, QQ Bot, Raft, Signal, Slack, SMS, Synology Chat, Tlon, Twitch, Voice Call, WhatsApp, Zalo, and Zalo Personal
- Channels maintained outside the OpenClaw repo as external plugins: WeChat, Yuanbao, and Zalo ClawBot
- Group chat works with mention-based activation
- DM safety relies on allowlists and pairing
Agent:
- Embedded agent runtime streams tool output
- Multi-agent routing keeps sessions isolated per workspace or sender
- Sessions: direct chats merge into a shared
main; groups stay isolated by default - Long responses use streaming and chunking
Auth and providers:
- Over 35 model providers (Anthropic, OpenAI, Google, and others)
- OAuth handles subscription auth (for example, OpenAI Codex)
- Custom and self-hosted providers are supported (vLLM, SGLang, Ollama, llama.cpp, LM Studio, and any OpenAI-compatible or Anthropic-compatible endpoint)
Media:
- Images, audio, video, and documents move in and out
- Audio and video play inline in the Control UI, iOS/macOS, Android, and the Linux companion
- Shared surfaces expose image generation and video generation capabilities
- Voice notes get transcribed
- Text-to-speech works with multiple providers
Apps and interfaces:
- WebChat plus browser Control UI
- macOS menu bar companion app
- iOS node with pairing, camera, screen recording, location, and voice
- Android node with pairing, chat, voice, camera, and device commands
Tools and automation:
- Browser automation, exec, sandboxing
- Web search (Brave, DuckDuckGo, Exa, Firecrawl, Gemini, Grok, Kimi, MiniMax Search, Ollama Web Search, Perplexity, SearXNG, Tavily)
- Cron jobs and heartbeat scheduling
- Skills, plugins, and workflow pipelines (Lobster)
Related
-
Experimental features, Opt-in capabilities not yet on the default surface.
-
Agent runtime, How the agent runtime model dispatches runs.
-
Channels, Link Telegram, WhatsApp, Discord, Slack, and more through one Gateway.
-
Plugins, Official and external plugins that extend OpenClaw.