​

Multi-Channel Integration

Access your agent from any messaging platform — 35+ channels with automatic format adaptation.

​

Supported Channels

​

Setup

Navigate to Settings > Channels in the GUI to connect a platform. Each channel has its own configuration panel with connection status indicators.

​

Message Types

All channels support:

• Text messages with platform-appropriate formatting
• Image / document / audio / video attachments (MediaType enum)
• File uploads with automatic type detection

​

Channel-Aware Output Adaptation

Myrm uses a dual-insurance architecture to ensure output renders correctly on every platform:

​

Pre-hoc Guidance (channel_output_hints)

At agent initialization, a channel-specific format hint is injected into the system prompt. This tells the LLM what the platform supports before it generates content:

• Telegram: “NO table syntax — use bullet lists or key: value pairs”
• WhatsApp: “Markdown does NOT render — use plain text only”
• Discord: “Messages over 2000 chars are split automatically”
• Voice: “Speak as you would to a person in conversation”

24 channel hints are pre-configured and KV-Cache safe (injected once at init).

​

Post-hoc Format Downgrade (renderer)

Even if the LLM ignores hints, the rendering pipeline applies format downgrades:

• supports_tables=false → Markdown tables converted to bullet lists
• supports_latex=false → LaTeX formulas stripped to plain text
• HTML/SVG code blocks replaced with short placeholders on IM channels
• Orphan citation markers auto-cleaned when no sources are present

​

Smart Message Splitting

Long messages are automatically split at natural boundaries:

• Code fence state machine ensures code blocks are properly closed and reopened across chunks
• Intelligent line splitting at whitespace and punctuation boundaries
• Configurable overflow tolerance for semantic preservation
• Per-channel length limits (e.g., Discord 2000 chars, Telegram 4096 chars)

​

Group Chat Features

​

AllowPolicy

Three preset policies control when the agent responds in group chats:

​

GroupContextBuffer

Non-trigger messages in group chats are accumulated in a per-group ring buffer. When a trigger message arrives (e.g., @agent), the buffer is drained and injected as context — giving the agent conversational awareness of the group discussion.

​

SessionGate

Rapid-fire messages from the same conversation are debounced (default 300ms window) and merged into a single request, preventing duplicate processing.

​

Agent-Initiated Notifications

Your agent can proactively push notifications to configured channels — no manual polling needed.

​

How It Works

1. Configure notification targets in your agent’s settings (channel + recipient whitelist)
2. The agent calls channel_notify_tool when it needs to alert you (task completion, anomaly detection, scheduled report ready)
3. The message is delivered through the ChannelGateway infrastructure with retry and dead-letter queue support

​

Security

​

Example Scenarios

• Scheduled task completes at 3 AM → agent sends summary to your Telegram
• Long-running code analysis finishes → results pushed to Slack channel
• Anomaly detected in monitored data → alert sent to configured notification target

​

Cross-Platform Handoff

Transfer a conversation from one platform to another without losing context. Use the /handoff command in any IM channel or the “Transfer to…” menu in Web UI. The handoff is instant (single DB update, millisecond latency) and preserves the full prompt cache.