agent-messenger

One CLI for Slack, Discord, Teams, Webex, Telegram, WhatsApp, LINE, Instagram, KakaoTalk, and Channel Talk. Credentials extracted from desktop apps and browsers, or authenticated in seconds — no API keys, no OAuth, no admin approval. TypeScript SDK included.

[!TIP] 🎉 Agent Messenger powers multi-channel messaging in TypeClaw, a TypeScript-native agent runtime.

Table of Contents

• Why Agent Messenger?
• Installation
• Agent Skills
  • SkillPad
  • Skills CLI
  • Claude Code Plugin
• Quick Start
• SDK
• TUI (Experimental)
• Supported Platforms
• Platform Guides
• Use Cases
  • Gathering Context
  • Communicating & Reporting
  • Automation & Pipelines
  • ...and More
• Philosophy
• Contributing
• Star History
• Thanks
• License

Why Agent Messenger?

You shouldn't need a bot token to send a message.

Every platform gates API access behind OAuth apps that need admin approval — days of waiting just to send a message. And even then, your agent is a bot, not you. Different name, different permissions, different context.

Agent Messenger reads session tokens from your Slack, Discord, Teams, KakaoTalk, or Channel Talk desktop app — zero config. If the desktop app isn't installed, it falls back to extracting from Chromium browsers, with auth extract --browser-profile <path> for custom Chromium profile locations. Webex and Instagram tokens are extracted directly from browsers. Telegram authenticates with a one-time phone code, and WhatsApp with a QR code or pairing code. Either way, your agent operates as you — same name, same permissions, same context. Bot tokens are fully supported too for server-side and CI/CD use cases.

• Auto-Extract Auth — Reads tokens from Slack, Discord, Teams, KakaoTalk, and Channel Talk desktop apps, with browser fallback and custom Chromium profile paths via --browser-profile. Webex and Instagram tokens extracted from Chromium browsers. Telegram and WhatsApp authenticate with a one-time code — still under a minute
• Act As Yourself — Extracts your user session — not a bot token. Your agent sends messages, reacts, and searches as you. Need bot mode? Bot CLIs are included too
• One Interface — Consistent command style across 7 platforms for supported actions (e.g. message send, message search, channel list, snapshot). Learn once
• Agent-Native Output — JSON by default for LLM tool use. --pretty for human-readable. Structured output your agent can parse and act on
• Token Efficient — CLI, not MCP. One skill file, one shell command per action. No server to run, no tool registration. (Why not MCP?)
• Persistent Memory — Stores workspace IDs, channel mappings, and preferences in ~/.config so your agent never asks twice
• TypeScript SDK — Import clients directly into your app. Full type safety with Zod schemas

Installation

CLI (global install for terminal / AI agent use):

npm install -g agent-messenger

SDK (project dependency for programmatic use):

npm install agent-messenger