stablyai/agent-slack

What it solves

agent-slack is a command-line interface (CLI) designed specifically for AI agents to automate Slack interactions. It solves the problem of providing agents with a token-efficient, easy-to-authenticate, and safe way to read, search, and write messages, manage channels, and handle files within Slack workspaces.

How it works

The tool is built with TypeScript and Bun, providing a set of commands for interacting with Slack's API. It focuses on three core principles:

• Token Efficiency: It outputs aggressively pruned JSON (removing null or empty fields) to reduce the cost and noise for LLMs.
• Zero-Config Auth: It automatically extracts authentication tokens from the Slack Desktop app or common web browsers (Chrome, Brave, Firefox) on macOS and Windows, removing the need for manual token management.
• Human-in-the-Loop: It includes a "Safe Mode" that redirects send, edit, and delete operations to a browser-based editor or drafts, ensuring no message is posted without human review.

Who it’s for

AI agent developers and users of agentic frameworks (like Claude Code, Codex, or Cursor) who want to give their agents the ability to to interact with Slack without complex API setup or high token overhead.

Highlights

• Agent-Ready Output: Pruned JSON outputs and automatic downloading of attached files to local paths for easy agent consumption.
• Safe Mode: Enforced human-in-the-loop review for all write operations to prevent AI-generated messages from being posted accidentally.
• Slack-Native Drafts: Ability to create and manage drafts that appear directly in the user's Slack client.
• Comprehensive Slack Control: Supports reading threads, searching messages/files, managing channels, and creating Slack canvases from Markdown.
• Rich Text Support: Automatically converts bullet and numbered lists into Slack's native rich text format.